How to fix: For Claude directory submission, declare the applicable annotations.readOnlyHint or annotations.destructiveHint value as a boolean on every tool.
How to fix: On each tool, declare annotations.readOnlyHint, annotations.destructiveHint, and annotations.openWorldHint as booleans. The policy review separately assesses whether their values match the tool's actual behavior.
The title clearly communicates the tool’s action and subject. Keep it concise.
Description74/100
Search projects, datasets, prompts, evaluators, or experiments in the current workspace. Use type to scope results and query to match names, keys, or descriptions.
The description explains the capability, when to use it, and what to expect.
Inputs70/100
4 of 5 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
limit
Not provided
Missing description. Explain what this value means and how to supply it.
starting_after
A cursor for use in pagination. `starting_after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, ending with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `starting_after=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the next page of the list.
Clear enough to supply this argument.
ending_before
A cursor for use in pagination. `ending_before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, starting with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `ending_before=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the previous page of the list.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
query
Optional case-insensitive text query matched against display_name, key, and description.
Clear enough to supply this argument.
type
Entity type to search. Use "prompt" to search prompt library entries. Use "evaluator" to search evaluators.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema81/100
The output schema explains the structured result.
View output schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"object",
"data",
"has_more"
],
"properties": {
"data": {
"type": "array",
"items": {
"type": "object",
"required": [
"_id",
"display_name"
],
"properties": {
"_id": {
"type": "string",
"description": "The unique identifier of the entity"
},
"key": {
"type": "string",
"description": "The key of the entity"
},
"created_at": {
"type": "string",
"default": "2026-10-14T21:39:36.699Z",
"description": "The date and time the entity was created"
},
"project_id": {
"type": [
"string",
"null"
],
"description": "The unique identifier of the project the entity belongs to"
},
"description": {
"type": [
"string",
"null"
],
"description": "The description of the entity"
},
"display_name": {
"type": "string",
"description": "The name of the entity"
}
},
"additionalProperties": false
}
},
"object": {
"type": "string",
"const": "list"
},
"has_more": {
"type": "boolean"
}
},
"additionalProperties": false
}
Original tool metadata
{
"name": "search_entities",
"title": "Search workspace entities",
"description": "Search projects, datasets, prompts, evaluators, or experiments in the current workspace. Use type to scope results and query to match names, keys, or descriptions.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"project",
"dataset",
"prompt",
"experiment",
"agent",
"knowledge",
"memory_store",
"deployment",
"evaluator",
"skill"
],
"type": "string",
"description": "Entity type to search. Use \"prompt\" to search prompt library entries. Use \"evaluator\" to search evaluators."
},
"limit": {
"type": "integer",
"default": 50,
"maximum": 100,
"minimum": 1
},
"query": {
"type": "string",
"minLength": 1,
"description": "Optional case-insensitive text query matched against display_name, key, and description."
},
"ending_before": {
"type": "string",
"description": "A cursor for use in pagination. `ending_before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, starting with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `ending_before=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the previous page of the list."
},
"starting_after": {
"type": "string",
"description": "A cursor for use in pagination. `starting_after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, ending with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `starting_after=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the next page of the list."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"object",
"data",
"has_more"
],
"properties": {
"data": {
"type": "array",
"items": {
"type": "object",
"required": [
"_id",
"display_name"
],
"properties": {
"_id": {
"type": "string",
"description": "The unique identifier of the entity"
},
"key": {
"type": "string",
"description": "The key of the entity"
},
"created_at": {
"type": "string",
"default": "2026-10-14T21:39:36.699Z",
"description": "The date and time the entity was created"
},
"project_id": {
"type": [
"string",
"null"
],
"description": "The unique identifier of the project the entity belongs to"
},
"description": {
"type": [
"string",
"null"
],
"description": "The description of the entity"
},
"display_name": {
"type": "string",
"description": "The name of the entity"
}
},
"additionalProperties": false
}
},
"object": {
"type": "string",
"const": "list"
},
"has_more": {
"type": "boolean"
}
},
"additionalProperties": false
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description54/100
Create a new dataset
Describe the concrete operation and its scope instead of restating the tool name.
Inputs0/100
0 of 2 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
display_name
Not provided
Missing description. Explain what this value means and how to supply it.
path
Not provided
Missing description. Explain what this value means and how to supply it.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema83/100
The output schema explains the structured result.
View output schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"_id",
"url"
],
"properties": {
"_id": {
"type": "string",
"description": "The id of the created dataset"
},
"url": {
"type": "string",
"description": "The direct link to access the dataset in the platform"
}
},
"additionalProperties": false
}
Original tool metadata
{
"name": "create_dataset",
"title": "Create Dataset",
"description": "Create a new dataset",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"display_name",
"path"
],
"properties": {
"path": {
"type": "string"
},
"display_name": {
"type": "string",
"maxLength": 128,
"minLength": 1
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"_id",
"url"
],
"properties": {
"_id": {
"type": "string",
"description": "The id of the created dataset"
},
"url": {
"type": "string",
"description": "The direct link to access the dataset in the platform"
}
},
"additionalProperties": false
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description57/100
List datapoints in a dataset
Describe the concrete operation and its scope instead of restating the tool name.
Inputs81/100
Explain the meaning of this value, not just its name.
dataset_id
The dataset ID
Explain the meaning of this value, not just its name.
starting_after
A cursor for use in pagination. `starting_after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, ending with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `starting_after=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the next page of the list.
Clear enough to supply this argument.
ending_before
A cursor for use in pagination. `ending_before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, starting with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `ending_before=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the previous page of the list.
Clear enough to supply this argument.
limit
The number of datapoints to return (max 25)
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema53/100
Describe the returned fields so an agent can interpret the result.
{
"name": "list_datapoints",
"title": "List Datapoints",
"description": "List datapoints in a dataset",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"dataset_id"
],
"properties": {
"limit": {
"type": "number",
"default": 10,
"maximum": 25,
"minimum": 1,
"description": "The number of datapoints to return (max 25)"
},
"dataset_id": {
"type": "string",
"description": "The dataset ID"
},
"ending_before": {
"type": "string",
"description": "A cursor for use in pagination. `ending_before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, starting with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `ending_before=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the previous page of the list."
},
"starting_after": {
"type": "string",
"description": "A cursor for use in pagination. `starting_after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, ending with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `starting_after=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the next page of the list."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"object",
"data",
"has_more"
],
"properties": {
"data": {
"type": "array",
"items": {
"type": "object",
"required": [
"_id"
],
"properties": {
"_id": {
"type": "string"
},
"inputs": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"expected_output": {
"type": "string"
}
},
"additionalProperties": false
}
},
"object": {
"type": "string",
"const": "list"
},
"has_more": {
"type": "boolean"
}
},
"additionalProperties": false
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description70/100
Delete one or more datapoints from a dataset
Explain mutations, irreversible effects, or prerequisites that matter before calling this tool.
Inputs63/100
Clarify units, where to obtain this value, or conventions not already expressed in the schema.
dataset_id
The id of the dataset to delete datapoints from
Clarify units, where to obtain this value, or conventions not already expressed in the schema.
datapoint_ids
The ids of the datapoints to delete
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema0/100
No output schema is declared. Add one for structured results so clients can interpret returned fields.
Not declared
Original tool metadata
{
"name": "delete_datapoints",
"title": "Delete Datapoints",
"description": "Delete one or more datapoints from a dataset",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"dataset_id",
"datapoint_ids"
],
"properties": {
"dataset_id": {
"type": "string",
"description": "The id of the dataset to delete datapoints from"
},
"datapoint_ids": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 100,
"minItems": 1,
"description": "The ids of the datapoints to delete"
}
}
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description67/100
Create a prompt deployment with a model configuration and messages. Use list_models to find valid chat model IDs. Messages support {{variable}} template syntax for dynamic content.
Describe the returned information so the agent knows whether it will answer the request.
Inputs65/100
11 of 13 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
key
Unique deployment key
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
description
Description of the deployment
Explain the meaning of this value, not just its name.
path
Project path where the deployment is stored, e.g. "Default/Deployments"
Clear enough to supply this argument.
variant › model
Model ID in "provider/model" format (e.g. "openai/gpt-4o"). Use list_models to find valid IDs.
Clear enough to supply this argument.
variant › messages › items › role
The message role
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
variant › messages › items › content
The message content. Supports {{variable}} template syntax.
Clear enough to supply this argument.
variant › temperature
Sampling temperature
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
variant › max_tokens
Maximum output tokens
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
variant › top_p
Top-p sampling
Explain the meaning of this value, not just its name.
variant › frequency_penalty
Frequency penalty
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
variant › presence_penalty
Presence penalty
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
variant › cache_control › type
Not provided
Missing description. Explain what this value means and how to supply it.
variant › cache_control › ttl
Not provided
Missing description. Explain what this value means and how to supply it.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema49/100
Describe the returned fields so an agent can interpret the result.
The title clearly communicates the tool’s action and subject. Keep it concise.
Description86/100
Search the orq.ai documentation for guides, API references, and tutorials. Returns matching pages with title, description, content snippet, and a direct link.
The description explains the capability, when to use it, and what to expect.
Inputs75/100
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
query
Search query to find relevant documentation pages.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
limit
Maximum number of results to return (1-50, default 10).
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema66/100
Describe the returned fields so an agent can interpret the result.
The title clearly communicates the tool’s action and subject. Keep it concise.
Description74/100
Create an LLM-as-a-Judge evaluator. The model must support function calling. Use list_models to find valid model IDs. The prompt can reference {{output.response}}, {{input.user_query}}, {{input.expected_output}}, {{input.all_messages}}, {{input.system_instructions}}, {{input.retrievals}} and {{output.tools_called}}. Legacy {{log.*}} variables are still supported.
The description explains the capability, when to use it, and what to expect.
Inputs26/100
6 of 19 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
path
Project path where the evaluator is stored, e.g. "Default/Evaluators"
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
prompt
LLM evaluation prompt. Use {{output.response}}, {{input.user_query}}, {{input.expected_output}}, {{input.all_messages}}, {{input.system_instructions}}, {{input.retrievals}} and {{output.tools_called}} as variables.
Clear enough to supply this argument.
model
Model ID in provider/model format, e.g. "openai/gpt-4o". Must support function calling.
Clear enough to supply this argument.
output_type
Output type of the evaluator (default: number)
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
description
Optional evaluator description
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
guardrail_config › anyOf › 0 › enabled
Not provided
Missing description. Explain what this value means and how to supply it.
guardrail_config › anyOf › 0 › alert_on_failure
Not provided
Missing description. Explain what this value means and how to supply it.
guardrail_config › anyOf › 0 › type
Not provided
Missing description. Explain what this value means and how to supply it.
guardrail_config › anyOf › 0 › value
Not provided
Missing description. Explain what this value means and how to supply it.
guardrail_config › anyOf › 1 › enabled
Not provided
Missing description. Explain what this value means and how to supply it.
guardrail_config › anyOf › 1 › alert_on_failure
Not provided
Missing description. Explain what this value means and how to supply it.
guardrail_config › anyOf › 1 › type
Not provided
Missing description. Explain what this value means and how to supply it.
guardrail_config › anyOf › 1 › values
Not provided
Missing description. Explain what this value means and how to supply it.
guardrail_config › anyOf › 2 › enabled
Not provided
Missing description. Explain what this value means and how to supply it.
guardrail_config › anyOf › 2 › alert_on_failure
Not provided
Missing description. Explain what this value means and how to supply it.
guardrail_config › anyOf › 2 › type
Not provided
Missing description. Explain what this value means and how to supply it.
guardrail_config › anyOf › 2 › value
Not provided
Missing description. Explain what this value means and how to supply it.
guardrail_config › anyOf › 2 › operator
Not provided
Missing description. Explain what this value means and how to supply it.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema0/100
No output schema is declared. Add one for structured results so clients can interpret returned fields.
Not declared
Original tool metadata
{
"name": "create_llm_eval",
"title": "Create LLM Evaluator",
"description": "Create an LLM-as-a-Judge evaluator. The model must support function calling. Use list_models to find valid model IDs. The prompt can reference {{output.response}}, {{input.user_query}}, {{input.expected_output}}, {{input.all_messages}}, {{input.system_instructions}}, {{input.retrievals}} and {{output.tools_called}}. Legacy {{log.*}} variables are still supported.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"key",
"path",
"prompt",
"model"
],
"properties": {
"key": {
"type": "string",
"pattern": "^[a-zA-Z0-9]([a-zA-Z0-9_-]*[a-zA-Z0-9])?$",
"minLength": 1,
"description": "Unique evaluator key (alphanumeric, dashes, underscores)"
},
"path": {
"type": "string",
"description": "Project path where the evaluator is stored, e.g. \"Default/Evaluators\""
},
"model": {
"type": "string",
"description": "Model ID in provider/model format, e.g. \"openai/gpt-4o\". Must support function calling."
},
"prompt": {
"type": "string",
"description": "LLM evaluation prompt. Use {{output.response}}, {{input.user_query}}, {{input.expected_output}}, {{input.all_messages}}, {{input.system_instructions}}, {{input.retrievals}} and {{output.tools_called}} as variables."
},
"description": {
"type": "string",
"default": "",
"description": "Optional evaluator description"
},
"output_type": {
"enum": [
"boolean",
"number",
"categorical",
"string"
],
"type": "string",
"default": "number",
"description": "Output type of the evaluator (default: number)"
},
"guardrail_config": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"value"
],
"properties": {
"type": {
"type": "string",
"const": "boolean"
},
"value": {
"type": "boolean"
},
"enabled": {
"type": "boolean",
"default": true
},
"alert_on_failure": {
"type": "boolean",
"default": false
}
}
},
{
"type": "object",
"required": [
"type",
"values"
],
"properties": {
"type": {
"type": "string",
"const": "categorical"
},
"values": {
"type": "array",
"items": {
"type": "string",
"minLength": 1
}
},
"enabled": {
"type": "boolean",
"default": true
},
"alert_on_failure": {
"type": "boolean",
"default": false
}
}
},
{
"type": "object",
"required": [
"type",
"value",
"operator"
],
"properties": {
"type": {
"type": "string",
"const": "number"
},
"value": {
"type": "number"
},
"enabled": {
"type": "boolean",
"default": true
},
"operator": {
"enum": [
"eq",
"ne",
"gt",
"gte",
"lt",
"lte"
],
"type": "string"
},
"alert_on_failure": {
"type": "boolean",
"default": false
}
}
}
],
"description": "Optional guardrail configuration. Type must match output_type."
}
}
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description67/100
Create a Python code evaluator. The code must define an `evaluate(log)` function that returns a boolean or number. The `log` dict has keys: input, output, reference, expected_output (a duplicate of reference), retrievals, messages and tool_calls.
The description explains the capability, when to use it, and what to expect.
Inputs22/100
5 of 18 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
The title clearly communicates the tool’s action and subject. Keep it concise.
Description87/100
Retrieve an LLM-as-a-Judge evaluator by its key or ID. Returns the full evaluator configuration including prompt, model, output type, mode, and description.
The description explains the capability, when to use it, and what to expect.
Inputs75/100
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
key
The evaluator key (display_name) or ID to look up
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema63/100
Describe the returned fields so an agent can interpret the result.
The title clearly communicates the tool’s action and subject. Keep it concise.
Description82/100
Update an existing LLM-as-a-Judge evaluator. Only the fields provided in updates will be changed; all other fields remain unchanged.
The description explains the capability, when to use it, and what to expect.
Inputs26/100
7 of 20 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
id
The evaluator ID
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
key
The evaluator key (display_name)
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
updates › key
New evaluator key (alphanumeric, dashes, underscores)
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
updates › description
New description
Explain the meaning of this value, not just its name.
updates › prompt
New LLM evaluation prompt. Use {{output.response}}, {{input.user_query}}, {{input.expected_output}}, {{input.all_messages}}, {{input.system_instructions}}, {{input.retrievals}} and {{output.tools_called}} as variables.
Clear enough to supply this argument.
updates › model
New model ID in provider/model format, e.g. "openai/gpt-4o". Must support function calling.
Clear enough to supply this argument.
updates › output_type
New output type
Explain the meaning of this value, not just its name.
The title clearly communicates the tool’s action and subject. Keep it concise.
Description91/100
Send feedback about orq.ai APIs, MCP tools, SDKs, or documentation by email to [email protected]. Include what happened and what you expected, with a request ID or relevant URL when available. Do not include API keys, tokens, passwords, or other secrets. Each submission sends a new email; do not retry automatically.
The description explains the capability, when to use it, and what to expect.
Inputs56/100
3 of 4 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
message
Feedback message
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
category
Not provided
Missing description. Explain what this value means and how to supply it.
request_id
Related request ID
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
url
Related HTTP or HTTPS URL
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Missing description. Explain what this value means and how to supply it.
input › anyOf › 1 › items › anyOf › 1 › type
Not provided
Missing description. Explain what this value means and how to supply it.
input › anyOf › 1 › items › anyOf › 1 › call_id
Not provided
Missing description. Explain what this value means and how to supply it.
input › anyOf › 1 › items › anyOf › 1 › output
Not provided
Missing description. Explain what this value means and how to supply it.
instructions
System-level instructions for the model.
Explain the meaning of this value, not just its name.
tools › items › type
Not provided
Missing description. Explain what this value means and how to supply it.
tools › items › name
Not provided
Missing description. Explain what this value means and how to supply it.
tools › items › description
Not provided
Missing description. Explain what this value means and how to supply it.
tools › items › parameters
Not provided
Missing description. Explain what this value means and how to supply it.
tools › items › strict
Not provided
Missing description. Explain what this value means and how to supply it.
tool_choice › anyOf › 1 › type
Not provided
Missing description. Explain what this value means and how to supply it.
tool_choice › anyOf › 1 › name
The name of the function tool to call.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
temperature
Not provided
Missing description. Explain what this value means and how to supply it.
top_p
Not provided
Missing description. Explain what this value means and how to supply it.
top_logprobs
Not provided
Missing description. Explain what this value means and how to supply it.
max_output_tokens
Not provided
Missing description. Explain what this value means and how to supply it.
max_tool_calls
Not provided
Missing description. Explain what this value means and how to supply it.
parallel_tool_calls
Not provided
Missing description. Explain what this value means and how to supply it.
previous_response_id
The ID of a previous response to continue a multi-turn conversation.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
metadata
Set of key-value pairs (max 16). Keys ≤64 chars, values ≤512 chars.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
store
Whether to store the response so it can be retrieved later.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
reasoning › effort
Not provided
Missing description. Explain what this value means and how to supply it.
reasoning › summary
Not provided
Missing description. Explain what this value means and how to supply it.
include
Additional fields to include in the response (e.g. "reasoning.encrypted_content", "message.output_text.logprobs"). Kept as free-form strings so new router-supported values do not require a schema bump; canonical enum is `includeEnumSchema` in @orq/responses/schemas.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id",
"object",
"created_at",
"completed_at",
"status",
"incomplete_details",
"model",
"previous_response_id",
"instructions",
"output",
"error",
"tools",
"truncation",
"parallel_tool_calls",
"text",
"top_p",
"presence_penalty",
"frequency_penalty",
"top_logprobs",
"temperature",
"reasoning",
"usage",
"max_output_tokens",
"max_tool_calls",
"store",
"background",
"service_tier",
"metadata",
"safety_identifier",
"prompt_cache_key",
"prompt_cache_retention",
"input",
"user"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the response that was created."
},
"text": {
"allOf": [
{
"type": "object",
"required": [
"format"
],
"properties": {
"format": {
"anyOf": [
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"json_object"
],
"type": "string",
"default": "json_object"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"name",
"description",
"schema",
"strict"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"json_schema"
],
"type": "string",
"default": "json_schema"
},
"schema": {
"type": "object",
"properties": {},
"additionalProperties": {}
},
"strict": {
"type": "boolean"
},
"description": {
"type": [
"string",
"null"
]
}
},
"additionalProperties": false
}
]
},
"verbosity": {
"enum": [
"low",
"medium",
"high"
],
"type": "string"
}
},
"additionalProperties": false
},
{}
]
},
"user": {
"type": [
"string",
"null"
]
},
"error": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"code",
"message"
],
"properties": {
"code": {
"type": "string",
"description": "A machine-readable error code that was returned."
},
"message": {
"type": "string",
"description": "A human-readable description of the error that was returned."
}
},
"description": "An error that occurred while generating the response.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"input": {
"type": "array",
"items": {},
"description": "Array of input items (messages, function call outputs, etc.)."
},
"model": {
"type": "string",
"description": "The model that generated this response."
},
"store": {
"type": "boolean",
"description": "Whether this response was stored so it can be retrieved later."
},
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"name",
"description",
"parameters",
"strict"
],
"properties": {
"name": {
"type": "string",
"description": "The name of the function to call."
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function",
"description": "The type of the function tool. Always `function`."
},
"strict": {
"type": [
"boolean",
"null"
]
},
"parameters": {
"anyOf": [
{
"type": "object",
"properties": {},
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"description": {
"type": [
"string",
"null"
]
}
},
"description": "A tool that can be used to generate a response.",
"additionalProperties": false
},
"description": "The tools that were available to the model during response generation."
},
"top_p": {
"type": "number",
"description": "The nucleus sampling parameter that was used for this response."
},
"usage": {
"anyOf": [
{
"type": "object",
"required": [
"input_tokens",
"output_tokens",
"total_tokens",
"input_tokens_details",
"output_tokens_details"
],
"properties": {
"input_cost": {
"type": "number",
"description": "Cost (USD) of input tokens. Present when billing was computed for this response."
},
"total_cost": {
"type": "number",
"description": "Total cost (USD) of the response. Present when billing was computed for this response."
},
"output_cost": {
"type": "number",
"description": "Cost (USD) of output tokens. Present when billing was computed for this response."
},
"input_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were used to generate the response."
},
"total_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The total number of tokens that were used."
},
"output_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of output tokens that were generated by the model."
},
"web_search_requests": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Number of web search tool invocations performed during the response."
},
"input_tokens_details": {
"type": "object",
"required": [
"cached_tokens"
],
"properties": {
"cached_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were served from cache."
},
"cache_creation_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were used to create a new cache entry (Anthropic prompt caching)."
},
"cache_creation_1h_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of cache_creation_tokens written to the 1-hour TTL cache (Anthropic prompt caching)."
},
"cache_creation_5m_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of cache_creation_tokens written to the 5-minute TTL cache (Anthropic prompt caching)."
}
},
"description": "A breakdown of input token usage that was recorded.",
"additionalProperties": {}
},
"output_tokens_details": {
"type": "object",
"required": [
"reasoning_tokens"
],
"properties": {
"reasoning_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of output tokens that were attributed to reasoning."
}
},
"description": "A breakdown of output token usage that was recorded.",
"additionalProperties": {}
}
},
"description": "Token usage statistics that were recorded for the response.",
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"entity": {
"type": "object",
"required": [
"type",
"id",
"key"
],
"properties": {
"id": {
"type": "string"
},
"key": {
"type": "string"
},
"type": {
"type": "string"
}
},
"description": "Entity (e.g. agent) that produced this response.",
"additionalProperties": false
},
"memory": {
"anyOf": [
{},
{
"type": "null"
}
],
"description": "orq.ai memory store reference attached to this response."
},
"object": {
"enum": [
"response"
],
"type": "string",
"default": "response",
"description": "The object type, which was always `response`."
},
"output": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"id",
"status",
"role",
"content"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the message."
},
"role": {
"allOf": [
{
"enum": [
"user",
"assistant",
"system",
"developer"
],
"type": "string"
},
{}
]
},
"type": {
"enum": [
"message"
],
"type": "string",
"default": "message",
"description": "The type of the message. Always set to `message`."
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string"
},
{}
]
},
"content": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"video_url"
],
"properties": {
"type": {
"enum": [
"input_video"
],
"type": "string",
"description": "The type of the input content. Always `input_video`."
},
"video_url": {
"type": "string",
"description": "A base64 or remote url that resolves to a video file."
}
},
"description": "A content block representing a video input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The content of the message"
}
},
"description": "A message to or from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"call_id",
"name",
"arguments",
"status"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the function call item."
},
"name": {
"type": "string",
"description": "The name of the function that was called."
},
"type": {
"enum": [
"function_call"
],
"type": "string",
"default": "function_call",
"description": "The type of the item. Always `function_call`."
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string"
},
{}
]
},
"call_id": {
"type": "string",
"description": "The unique ID of the function tool call that was generated."
},
"arguments": {
"type": "string",
"description": "The arguments JSON string that was generated."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
}
},
"description": "A function tool call that was generated by the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"call_id",
"output",
"status"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the function tool call output. Populated when this item is returned via API."
},
"type": {
"enum": [
"function_call_output"
],
"type": "string",
"default": "function_call_output",
"description": "The type of the function tool call output. Always `function_call_output`."
},
"output": {
"anyOf": [
{
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
}
},
{
"type": "string"
}
]
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string",
"description": "Similar to `FunctionCallStatus`. All three options are allowed here for compatibility, but because in practice these items will be provided by developers, only `completed` should be used."
},
{}
]
},
"call_id": {
"type": "string",
"description": "The unique ID of the function tool call generated by the model."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
}
},
"description": "A function tool call output that was returned by the tool.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"summary"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the reasoning item."
},
"type": {
"enum": [
"reasoning"
],
"type": "string",
"default": "reasoning",
"description": "The type of the item. Always `reasoning`."
},
"content": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The reasoning content that was generated."
},
"summary": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The reasoning summary content that was generated."
},
"signature": {
"type": "string",
"description": "The signature of the reasoning content that was generated."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
},
"encrypted_content": {
"type": "string",
"description": "The encrypted reasoning content that was generated."
}
},
"description": "A reasoning item that was generated by the model.",
"additionalProperties": false
},
{
"allOf": [
{
"type": "object",
"required": [
"id",
"type",
"status",
"result"
],
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"result": {},
"status": {
"type": "string"
}
},
"additionalProperties": false
},
{}
]
}
],
"description": "An item representing a message, tool call, tool output, reasoning, or other response element."
},
"description": "The output items that were generated by the model."
},
"status": {
"type": "string",
"description": "The status that was set for the response."
},
"metadata": {
"description": "Developer-defined metadata that was associated with the response."
},
"reasoning": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"effort",
"summary"
],
"properties": {
"effort": {
"anyOf": [
{
"enum": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
],
"type": "string"
},
{
"type": "null"
}
]
},
"summary": {
"anyOf": [
{
"allOf": [
{
"enum": [
"concise",
"detailed",
"auto"
],
"type": "string"
},
{}
]
},
{
"type": "null"
}
]
}
},
"description": "Reasoning configuration and metadata that were used for the response.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"telemetry": {
"type": "object",
"required": [
"trace_id",
"span_id"
],
"properties": {
"span_id": {
"type": "string"
},
"trace_id": {
"type": "string"
}
},
"description": "OpenTelemetry identifiers for this response.",
"additionalProperties": false
},
"variables": {
"type": "object",
"description": "Template variables that were applied when rendering this response.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"background": {
"type": "boolean",
"description": "Whether this request was run in the background."
},
"created_at": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The Unix timestamp (in seconds) for when the response was created."
},
"project_id": {
"type": [
"string",
"null"
],
"description": "Project ID associated with the entity that produced this response."
},
"truncation": {
"allOf": [
{
"enum": [
"auto",
"disabled"
],
"type": "string"
},
{}
]
},
"output_text": {
"type": "string",
"description": "Convenience field aggregating text from output items. Added by the OpenAI SDK on parse."
},
"temperature": {
"type": "number",
"description": "The sampling temperature that was used for this response."
},
"tool_choice": {
"anyOf": [
{
"type": "object",
"required": [
"type"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function"
}
},
"additionalProperties": false
},
{
"enum": [
"none",
"auto",
"required"
],
"type": "string"
},
{
"type": "object",
"required": [
"type",
"tools",
"mode"
],
"properties": {
"mode": {
"enum": [
"none",
"auto",
"required"
],
"type": "string"
},
"type": {
"enum": [
"allowed_tools"
],
"type": "string",
"default": "allowed_tools"
},
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"type"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function"
}
},
"additionalProperties": false
}
}
},
"additionalProperties": false
}
]
},
"completed_at": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"conversation": {
"anyOf": [
{},
{
"type": "null"
}
],
"description": "orq.ai conversation context attached to this response."
},
"instructions": {
"type": [
"string",
"null"
]
},
"service_tier": {
"type": "string",
"description": "The service tier that was used for this response."
},
"top_logprobs": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of most likely tokens that were returned at each position, along with their log probabilities."
},
"max_tool_calls": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"presence_penalty": {
"type": "number",
"description": "The presence penalty that was used to penalize new tokens based on whether they appear in the text so far."
},
"prompt_cache_key": {
"type": [
"string",
"null"
]
},
"frequency_penalty": {
"type": "number",
"description": "The frequency penalty that was used to penalize new tokens based on their frequency in the text so far."
},
"max_output_tokens": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"safety_identifier": {
"type": [
"string",
"null"
]
},
"incomplete_details": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"reason"
],
"properties": {
"reason": {
"type": "string",
"description": "The reason the response could not be completed."
}
},
"description": "Details about why the response was incomplete.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"parallel_tool_calls": {
"type": "boolean",
"description": "Whether the model was allowed to call multiple tools in parallel."
},
"previous_response_id": {
"type": [
"string",
"null"
]
},
"prompt_cache_retention": {
"type": [
"string",
"null"
]
}
},
"description": "The complete response object that was returned by the Responses API.",
"additionalProperties": {}
}
Original tool metadata
{
"name": "invoke_model",
"title": "Invoke Model",
"description": "Invoke a model using the Responses API. The model param must follow the format \"provider/model\". Returns the full response resource.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"model"
],
"properties": {
"input": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"role",
"content"
],
"properties": {
"role": {
"enum": [
"user",
"system",
"assistant",
"developer"
],
"type": "string"
},
"content": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"type": "string",
"const": "input_text"
}
}
}
}
]
}
}
},
{
"type": "object",
"required": [
"type",
"call_id",
"output"
],
"properties": {
"type": {
"type": "string",
"const": "function_call_output"
},
"output": {
"type": "string"
},
"call_id": {
"type": "string",
"minLength": 1
}
}
}
]
}
}
],
"description": "The input to send to the model. Can be a string or an array of input items."
},
"model": {
"type": "string",
"minLength": 1,
"description": "The model to use in the format \"provider/model\" (e.g. \"openai/gpt-4o\", \"anthropic/claude-sonnet-4-20250514\")."
},
"store": {
"type": "boolean",
"description": "Whether to store the response so it can be retrieved later."
},
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"pattern": "^[a-zA-Z0-9_-]+$",
"maxLength": 64,
"minLength": 1
},
"type": {
"type": "string",
"const": "function",
"default": "function"
},
"strict": {
"type": "boolean"
},
"parameters": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"description": {
"type": "string"
}
}
},
"description": "Function tools available to the model."
},
"top_p": {
"type": "number",
"maximum": 1,
"minimum": 0
},
"include": {
"type": "array",
"items": {
"type": "string"
},
"description": "Additional fields to include in the response (e.g. \"reasoning.encrypted_content\", \"message.output_text.logprobs\"). Kept as free-form strings so new router-supported values do not require a schema bump; canonical enum is `includeEnumSchema` in @orq/responses/schemas."
},
"metadata": {
"type": "object",
"description": "Set of key-value pairs (max 16). Keys ≤64 chars, values ≤512 chars.",
"propertyNames": {
"type": "string",
"maxLength": 64
},
"additionalProperties": {
"type": "string",
"maxLength": 512
}
},
"reasoning": {
"type": "object",
"properties": {
"effort": {
"anyOf": [
{
"enum": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
],
"type": "string"
},
{
"type": "null"
}
]
},
"summary": {
"anyOf": [
{
"allOf": [
{
"enum": [
"concise",
"detailed",
"auto"
],
"type": "string"
},
{}
]
},
{
"type": "null"
}
]
}
},
"description": "Reasoning controls for reasoning-capable models (gpt-5, o-series)."
},
"temperature": {
"type": "number",
"maximum": 2,
"minimum": 0
},
"tool_choice": {
"anyOf": [
{
"enum": [
"none",
"auto",
"required"
],
"type": "string"
},
{
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"minLength": 1,
"description": "The name of the function tool to call."
},
"type": {
"type": "string",
"const": "function",
"default": "function"
}
}
}
],
"description": "Controls which tool the model should use."
},
"instructions": {
"type": "string",
"description": "System-level instructions for the model."
},
"top_logprobs": {
"type": "integer",
"maximum": 20,
"minimum": 0
},
"max_tool_calls": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": 1
},
"max_output_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": 1
},
"parallel_tool_calls": {
"type": "boolean"
},
"previous_response_id": {
"type": "string",
"description": "The ID of a previous response to continue a multi-turn conversation."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id",
"object",
"created_at",
"completed_at",
"status",
"incomplete_details",
"model",
"previous_response_id",
"instructions",
"output",
"error",
"tools",
"truncation",
"parallel_tool_calls",
"text",
"top_p",
"presence_penalty",
"frequency_penalty",
"top_logprobs",
"temperature",
"reasoning",
"usage",
"max_output_tokens",
"max_tool_calls",
"store",
"background",
"service_tier",
"metadata",
"safety_identifier",
"prompt_cache_key",
"prompt_cache_retention",
"input",
"user"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the response that was created."
},
"text": {
"allOf": [
{
"type": "object",
"required": [
"format"
],
"properties": {
"format": {
"anyOf": [
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"json_object"
],
"type": "string",
"default": "json_object"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"name",
"description",
"schema",
"strict"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"json_schema"
],
"type": "string",
"default": "json_schema"
},
"schema": {
"type": "object",
"properties": {},
"additionalProperties": {}
},
"strict": {
"type": "boolean"
},
"description": {
"type": [
"string",
"null"
]
}
},
"additionalProperties": false
}
]
},
"verbosity": {
"enum": [
"low",
"medium",
"high"
],
"type": "string"
}
},
"additionalProperties": false
},
{}
]
},
"user": {
"type": [
"string",
"null"
]
},
"error": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"code",
"message"
],
"properties": {
"code": {
"type": "string",
"description": "A machine-readable error code that was returned."
},
"message": {
"type": "string",
"description": "A human-readable description of the error that was returned."
}
},
"description": "An error that occurred while generating the response.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"input": {
"type": "array",
"items": {},
"description": "Array of input items (messages, function call outputs, etc.)."
},
"model": {
"type": "string",
"description": "The model that generated this response."
},
"store": {
"type": "boolean",
"description": "Whether this response was stored so it can be retrieved later."
},
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"name",
"description",
"parameters",
"strict"
],
"properties": {
"name": {
"type": "string",
"description": "The name of the function to call."
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function",
"description": "The type of the function tool. Always `function`."
},
"strict": {
"type": [
"boolean",
"null"
]
},
"parameters": {
"anyOf": [
{
"type": "object",
"properties": {},
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"description": {
"type": [
"string",
"null"
]
}
},
"description": "A tool that can be used to generate a response.",
"additionalProperties": false
},
"description": "The tools that were available to the model during response generation."
},
"top_p": {
"type": "number",
"description": "The nucleus sampling parameter that was used for this response."
},
"usage": {
"anyOf": [
{
"type": "object",
"required": [
"input_tokens",
"output_tokens",
"total_tokens",
"input_tokens_details",
"output_tokens_details"
],
"properties": {
"input_cost": {
"type": "number",
"description": "Cost (USD) of input tokens. Present when billing was computed for this response."
},
"total_cost": {
"type": "number",
"description": "Total cost (USD) of the response. Present when billing was computed for this response."
},
"output_cost": {
"type": "number",
"description": "Cost (USD) of output tokens. Present when billing was computed for this response."
},
"input_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were used to generate the response."
},
"total_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The total number of tokens that were used."
},
"output_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of output tokens that were generated by the model."
},
"web_search_requests": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Number of web search tool invocations performed during the response."
},
"input_tokens_details": {
"type": "object",
"required": [
"cached_tokens"
],
"properties": {
"cached_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were served from cache."
},
"cache_creation_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were used to create a new cache entry (Anthropic prompt caching)."
},
"cache_creation_1h_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of cache_creation_tokens written to the 1-hour TTL cache (Anthropic prompt caching)."
},
"cache_creation_5m_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of cache_creation_tokens written to the 5-minute TTL cache (Anthropic prompt caching)."
}
},
"description": "A breakdown of input token usage that was recorded.",
"additionalProperties": {}
},
"output_tokens_details": {
"type": "object",
"required": [
"reasoning_tokens"
],
"properties": {
"reasoning_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of output tokens that were attributed to reasoning."
}
},
"description": "A breakdown of output token usage that was recorded.",
"additionalProperties": {}
}
},
"description": "Token usage statistics that were recorded for the response.",
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"entity": {
"type": "object",
"required": [
"type",
"id",
"key"
],
"properties": {
"id": {
"type": "string"
},
"key": {
"type": "string"
},
"type": {
"type": "string"
}
},
"description": "Entity (e.g. agent) that produced this response.",
"additionalProperties": false
},
"memory": {
"anyOf": [
{},
{
"type": "null"
}
],
"description": "orq.ai memory store reference attached to this response."
},
"object": {
"enum": [
"response"
],
"type": "string",
"default": "response",
"description": "The object type, which was always `response`."
},
"output": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"id",
"status",
"role",
"content"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the message."
},
"role": {
"allOf": [
{
"enum": [
"user",
"assistant",
"system",
"developer"
],
"type": "string"
},
{}
]
},
"type": {
"enum": [
"message"
],
"type": "string",
"default": "message",
"description": "The type of the message. Always set to `message`."
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string"
},
{}
]
},
"content": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"video_url"
],
"properties": {
"type": {
"enum": [
"input_video"
],
"type": "string",
"description": "The type of the input content. Always `input_video`."
},
"video_url": {
"type": "string",
"description": "A base64 or remote url that resolves to a video file."
}
},
"description": "A content block representing a video input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The content of the message"
}
},
"description": "A message to or from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"call_id",
"name",
"arguments",
"status"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the function call item."
},
"name": {
"type": "string",
"description": "The name of the function that was called."
},
"type": {
"enum": [
"function_call"
],
"type": "string",
"default": "function_call",
"description": "The type of the item. Always `function_call`."
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string"
},
{}
]
},
"call_id": {
"type": "string",
"description": "The unique ID of the function tool call that was generated."
},
"arguments": {
"type": "string",
"description": "The arguments JSON string that was generated."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
}
},
"description": "A function tool call that was generated by the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"call_id",
"output",
"status"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the function tool call output. Populated when this item is returned via API."
},
"type": {
"enum": [
"function_call_output"
],
"type": "string",
"default": "function_call_output",
"description": "The type of the function tool call output. Always `function_call_output`."
},
"output": {
"anyOf": [
{
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
}
},
{
"type": "string"
}
]
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string",
"description": "Similar to `FunctionCallStatus`. All three options are allowed here for compatibility, but because in practice these items will be provided by developers, only `completed` should be used."
},
{}
]
},
"call_id": {
"type": "string",
"description": "The unique ID of the function tool call generated by the model."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
}
},
"description": "A function tool call output that was returned by the tool.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"summary"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the reasoning item."
},
"type": {
"enum": [
"reasoning"
],
"type": "string",
"default": "reasoning",
"description": "The type of the item. Always `reasoning`."
},
"content": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The reasoning content that was generated."
},
"summary": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The reasoning summary content that was generated."
},
"signature": {
"type": "string",
"description": "The signature of the reasoning content that was generated."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
},
"encrypted_content": {
"type": "string",
"description": "The encrypted reasoning content that was generated."
}
},
"description": "A reasoning item that was generated by the model.",
"additionalProperties": false
},
{
"allOf": [
{
"type": "object",
"required": [
"id",
"type",
"status",
"result"
],
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"result": {},
"status": {
"type": "string"
}
},
"additionalProperties": false
},
{}
]
}
],
"description": "An item representing a message, tool call, tool output, reasoning, or other response element."
},
"description": "The output items that were generated by the model."
},
"status": {
"type": "string",
"description": "The status that was set for the response."
},
"metadata": {
"description": "Developer-defined metadata that was associated with the response."
},
"reasoning": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"effort",
"summary"
],
"properties": {
"effort": {
"anyOf": [
{
"enum": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
],
"type": "string"
},
{
"type": "null"
}
]
},
"summary": {
"anyOf": [
{
"allOf": [
{
"enum": [
"concise",
"detailed",
"auto"
],
"type": "string"
},
{}
]
},
{
"type": "null"
}
]
}
},
"description": "Reasoning configuration and metadata that were used for the response.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"telemetry": {
"type": "object",
"required": [
"trace_id",
"span_id"
],
"properties": {
"span_id": {
"type": "string"
},
"trace_id": {
"type": "string"
}
},
"description": "OpenTelemetry identifiers for this response.",
"additionalProperties": false
},
"variables": {
"type": "object",
"description": "Template variables that were applied when rendering this response.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"background": {
"type": "boolean",
"description": "Whether this request was run in the background."
},
"created_at": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The Unix timestamp (in seconds) for when the response was created."
},
"project_id": {
"type": [
"string",
"null"
],
"description": "Project ID associated with the entity that produced this response."
},
"truncation": {
"allOf": [
{
"enum": [
"auto",
"disabled"
],
"type": "string"
},
{}
]
},
"output_text": {
"type": "string",
"description": "Convenience field aggregating text from output items. Added by the OpenAI SDK on parse."
},
"temperature": {
"type": "number",
"description": "The sampling temperature that was used for this response."
},
"tool_choice": {
"anyOf": [
{
"type": "object",
"required": [
"type"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function"
}
},
"additionalProperties": false
},
{
"enum": [
"none",
"auto",
"required"
],
"type": "string"
},
{
"type": "object",
"required": [
"type",
"tools",
"mode"
],
"properties": {
"mode": {
"enum": [
"none",
"auto",
"required"
],
"type": "string"
},
"type": {
"enum": [
"allowed_tools"
],
"type": "string",
"default": "allowed_tools"
},
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"type"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function"
}
},
"additionalProperties": false
}
}
},
"additionalProperties": false
}
]
},
"completed_at": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"conversation": {
"anyOf": [
{},
{
"type": "null"
}
],
"description": "orq.ai conversation context attached to this response."
},
"instructions": {
"type": [
"string",
"null"
]
},
"service_tier": {
"type": "string",
"description": "The service tier that was used for this response."
},
"top_logprobs": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of most likely tokens that were returned at each position, along with their log probabilities."
},
"max_tool_calls": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"presence_penalty": {
"type": "number",
"description": "The presence penalty that was used to penalize new tokens based on whether they appear in the text so far."
},
"prompt_cache_key": {
"type": [
"string",
"null"
]
},
"frequency_penalty": {
"type": "number",
"description": "The frequency penalty that was used to penalize new tokens based on their frequency in the text so far."
},
"max_output_tokens": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"safety_identifier": {
"type": [
"string",
"null"
]
},
"incomplete_details": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"reason"
],
"properties": {
"reason": {
"type": "string",
"description": "The reason the response could not be completed."
}
},
"description": "Details about why the response was incomplete.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"parallel_tool_calls": {
"type": "boolean",
"description": "Whether the model was allowed to call multiple tools in parallel."
},
"previous_response_id": {
"type": [
"string",
"null"
]
},
"prompt_cache_retention": {
"type": [
"string",
"null"
]
}
},
"description": "The complete response object that was returned by the Responses API.",
"additionalProperties": {}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description91/100
Export an experiment run and return a signed download URL. The file contains the full row data including inputs, outputs, evaluator scores, cost, and latency.
The description explains the capability, when to use it, and what to expect.
Inputs58/100
Clarify units, where to obtain this value, or conventions not already expressed in the schema.
run_id
The experiment run ID to export
Clarify units, where to obtain this value, or conventions not already expressed in the schema.
experiment_id
The parent sheet/experiment ID
Clarify units, where to obtain this value, or conventions not already expressed in the schema.
format
Export file format (default: jsonl)
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema0/100
No output schema is declared. Add one for structured results so clients can interpret returned fields.
Not declared
Original tool metadata
{
"name": "get_experiment_run",
"title": "Get Experiment Run",
"description": "Export an experiment run and return a signed download URL. The file contains the full row data including inputs, outputs, evaluator scores, cost, and latency.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"run_id",
"experiment_id"
],
"properties": {
"format": {
"enum": [
"json",
"jsonl",
"csv"
],
"type": "string",
"default": "jsonl",
"description": "Export file format (default: jsonl)"
},
"run_id": {
"type": "string",
"description": "The experiment run ID to export"
},
"experiment_id": {
"type": "string",
"description": "The parent sheet/experiment ID"
}
}
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description70/100
Create an experiment from a dataset. Specify task type: "prompt" with model configurations, or "agent" with agent keys. Use auto_run to queue for immediate execution.
Describe the returned information so the agent knows whether it will answer the request.
Inputs21/100
12 of 45 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
Missing description. Explain what this value means and how to supply it.
experiment › evaluators › items › id
Not provided
Missing description. Explain what this value means and how to supply it.
auto_run
Queue the experiment for immediate execution
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema81/100
The output schema explains the structured result.
View output schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"experiment_id",
"run_id",
"status",
"url"
],
"properties": {
"url": {
"type": "string",
"description": "The direct link to access the experiment in the platform"
},
"run_id": {
"type": "string",
"description": "The experiment run (manifest) ID. Use this with get_experiment_run."
},
"status": {
"type": "string",
"description": "Experiment run status"
},
"experiment_id": {
"type": "string",
"description": "The experiment (sheet) ID. Use this with delete_entity(type: \"experiment\")."
}
},
"additionalProperties": false
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description64/100
Create a new skill. Skills are modular markdown instructions that codify processes or conventions.
Describe the concrete operation and its scope instead of restating the tool name.
Inputs63/100
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
display_name
Unique display name for the skill within the workspace. Must start with a letter; only letters, numbers, dashes, and underscores are allowed. Dots are not allowed because they separate the template path in {{skill.<name>}}.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
description
Short description of what the skill does
Explain the meaning of this value, not just its name.
tags
Tags for organizing skills
Explain the meaning of this value, not just its name.
path
Finder path for the skill. If project_id is also given, every segment is treated as a folder inside that project (a leading segment matching the project's display name, or "default", is stripped); otherwise the first segment must be the display name of an existing project in the workspace and any further segments are folders. Folders are created if missing, e.g. "MyProject/Skills". Either path or project_id is required — prefer project_id when you know it.
Clear enough to supply this argument.
project_id
Project ID to scope the skill to a project. Either path or project_id is required
Clarify units, where to obtain this value, or conventions not already expressed in the schema.
instructions
Skill instructions - the modular markdown content
Explain the meaning of this value, not just its name.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema0/100
No output schema is declared. Add one for structured results so clients can interpret returned fields.
Not declared
Original tool metadata
{
"name": "create_skill",
"title": "Create Skill",
"description": "Create a new skill. Skills are modular markdown instructions that codify processes or conventions.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"display_name"
],
"properties": {
"path": {
"type": "string",
"description": "Finder path for the skill. If project_id is also given, every segment is treated as a folder inside that project (a leading segment matching the project's display name, or \"default\", is stripped); otherwise the first segment must be the display name of an existing project in the workspace and any further segments are folders. Folders are created if missing, e.g. \"MyProject/Skills\". Either path or project_id is required — prefer project_id when you know it."
},
"tags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Tags for organizing skills"
},
"project_id": {
"type": "string",
"description": "Project ID to scope the skill to a project. Either path or project_id is required"
},
"description": {
"type": "string",
"description": "Short description of what the skill does"
},
"display_name": {
"type": "string",
"pattern": "^[A-Za-z][A-Za-z0-9]*(?:[_-][A-Za-z0-9]+)*$",
"maxLength": 255,
"minLength": 1,
"description": "Unique display name for the skill within the workspace. Must start with a letter; only letters, numbers, dashes, and underscores are allowed. Dots are not allowed because they separate the template path in {{skill.<name>}}."
},
"instructions": {
"type": "string",
"description": "Skill instructions - the modular markdown content"
}
}
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description88/100
Retrieve a skill by its ID. Returns the full skill configuration including instructions.
The description explains the capability, when to use it, and what to expect.
Inputs75/100
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
skill_id
The ID of the skill to retrieve
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema0/100
No output schema is declared. Add one for structured results so clients can interpret returned fields.
Not declared
Original tool metadata
{
"name": "get_skill",
"title": "Get Skill",
"description": "Retrieve a skill by its ID. Returns the full skill configuration including instructions.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"skill_id"
],
"properties": {
"skill_id": {
"type": "string",
"minLength": 1,
"description": "The ID of the skill to retrieve"
}
}
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description82/100
Update an existing skill. Only the fields provided will change; omitted fields keep their current values.
The description explains the capability, when to use it, and what to expect.
Inputs71/100
Clarify units, where to obtain this value, or conventions not already expressed in the schema.
skill_id
The ID of the skill to update
Clarify units, where to obtain this value, or conventions not already expressed in the schema.
display_name
New display name for the skill. Must start with a letter; only letters, numbers, dashes, and underscores are allowed. Dots are not allowed.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
description
New description
Explain the meaning of this value, not just its name.
tags
Replacement list of tags. Pass an empty array to clear all tags.
Clear enough to supply this argument.
path
New finder path for the skill. If the skill belongs to a project, or project_id is given, the path is resolved inside that project (a leading segment matching the project's display name, or "default", is stripped); otherwise the first segment must be the display name of an existing project, e.g. "MyProject/Skills". Folders are created if missing. Pass the empty string ("") to detach the skill from its project and move it to the workspace root; a whitespace-only string (e.g. " ") is rejected.
Clear enough to supply this argument.
project_id
Move the skill to this project. Without path, the skill is stored at the project root and its path is set to the project display name. Pass the empty string (""), or an empty path, to move the skill to the workspace root; a whitespace-only string is rejected.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
instructions
Replacement instructions markdown
Explain the meaning of this value, not just its name.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema0/100
No output schema is declared. Add one for structured results so clients can interpret returned fields.
Not declared
Original tool metadata
{
"name": "update_skill",
"title": "Update Skill",
"description": "Update an existing skill. Only the fields provided will change; omitted fields keep their current values.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"skill_id"
],
"properties": {
"path": {
"type": "string",
"description": "New finder path for the skill. If the skill belongs to a project, or project_id is given, the path is resolved inside that project (a leading segment matching the project's display name, or \"default\", is stripped); otherwise the first segment must be the display name of an existing project, e.g. \"MyProject/Skills\". Folders are created if missing. Pass the empty string (\"\") to detach the skill from its project and move it to the workspace root; a whitespace-only string (e.g. \" \") is rejected."
},
"tags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Replacement list of tags. Pass an empty array to clear all tags."
},
"skill_id": {
"type": "string",
"minLength": 1,
"description": "The ID of the skill to update"
},
"project_id": {
"type": "string",
"description": "Move the skill to this project. Without path, the skill is stored at the project root and its path is set to the project display name. Pass the empty string (\"\"), or an empty path, to move the skill to the workspace root; a whitespace-only string is rejected."
},
"description": {
"type": "string",
"description": "New description"
},
"display_name": {
"type": "string",
"pattern": "^[A-Za-z][A-Za-z0-9]*(?:[_-][A-Za-z0-9]+)*$",
"maxLength": 255,
"minLength": 1,
"description": "New display name for the skill. Must start with a letter; only letters, numbers, dashes, and underscores are allowed. Dots are not allowed."
},
"instructions": {
"type": "string",
"description": "Replacement instructions markdown"
}
}
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description83/100
List traces for a workspace with filtering support.
Available filters:
- model: Filter by LLM model (e.g. "gpt-4o", "claude-sonnet-4-20250514")
- type: Filter by leading span type (e.g. "generation", "retrieval", "agent")
- entity_key: Filter by deployment/entity key
- project_id: Filter by project ID
- trace_id: Filter by specific trace ID
- thread_id: Filter by thread ID
- identity_id: Filter by contact/identity ID (e.g. "contact_01ARZ3NDEKTSV4RRFFQ69G5FAV")
- search: Full-text search across trace fields
- start_time_after: Only return traces starting after this time (ISO 8601)
- start_time_before: Only return traces starting before this time (ISO 8601)
Without time bounds, searches the last 24 hours. An end time alone searches the 24 hours ending at that time. A start time alone searches from that time until now. The applied window is returned in metadata and preserved across cursor pages.
Annotation/evaluation filters:
- evaluator_key: Filter by annotation/evaluator key OR id (e.g. "rating" or "01HXXX...")
- eval_score_min: Minimum evaluation score (inclusive)
- eval_score_max: Maximum evaluation score (inclusive)
- eval_passed: Filter by passed status (true/false)
- eval_label: Filter by evaluation label value
Results are sorted by timestamp descending (most recent first).
Describe the returned information so the agent knows whether it will answer the request.
Inputs72/100
16 of 17 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
limit
Not provided
Missing description. Explain what this value means and how to supply it.
cursor
Opaque cursor token returned by the previous call; null/undefined for first page
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
model
Filter by LLM model name (e.g. "gpt-4o")
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
type
Filter by leading span type (e.g. "generation", "retrieval", "agent")
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
entity_key
Filter by deployment/entity key
Explain the meaning of this value, not just its name.
project_id
Filter by project ID
Explain the meaning of this value, not just its name.
trace_id
Filter by trace ID
Explain the meaning of this value, not just its name.
thread_id
Filter by thread ID
Clear enough to supply this argument.
identity_id
Filter by contact/identity ID
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
search
Full-text search across trace fields
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
start_time_after
Only return traces starting after this time (ISO 8601, e.g. "2026-03-01T00:00:00Z")
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
start_time_before
Only return traces starting before this time (ISO 8601, e.g. "2026-03-23T23:59:59Z")
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
evaluator_key
Filter by annotation/evaluator key OR id (e.g. "rating" or "01HXXX...")
Clear enough to supply this argument.
eval_score_min
Minimum evaluation score (inclusive)
Clear enough to supply this argument.
eval_score_max
Maximum evaluation score (inclusive)
Clear enough to supply this argument.
eval_passed
Filter by evaluation passed status
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
eval_label
Filter by evaluation label value
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema49/100
Describe the returned fields so an agent can interpret the result.
The title clearly communicates the tool’s action and subject. Keep it concise.
Description82/100
Retrieve a single span by its ID. Use mode "compact" for metadata only (fast) or "full" to include the complete input/output content (slower).
The description explains the capability, when to use it, and what to expect.
Inputs63/100
Clarify units, where to obtain this value, or conventions not already expressed in the schema.
span_id
Unique identifier of the span
Clarify units, where to obtain this value, or conventions not already expressed in the schema.
mode
compact = metadata only; full = include full input/output content
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema0/100
No output schema is declared. Add one for structured results so clients can interpret returned fields.
Not declared
Original tool metadata
{
"name": "get_span",
"title": "Retrieve Trace Span",
"description": "Retrieve a single span by its ID. Use mode \"compact\" for metadata only (fast) or \"full\" to include the complete input/output content (slower).",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"span_id"
],
"properties": {
"mode": {
"enum": [
"compact",
"full"
],
"type": "string",
"default": "compact",
"description": "compact = metadata only; full = include full input/output content"
},
"span_id": {
"type": "string",
"description": "Unique identifier of the span"
}
}
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description94/100
List all spans belonging to a specific trace. Returns span data (id, name, type, timing, parent_id) for tree reconstruction. Use get_span with mode "full" to retrieve input/output content for individual spans.
The description explains the capability, when to use it, and what to expect.
Inputs42/100
2 of 3 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
limit
Not provided
Missing description. Explain what this value means and how to supply it.
cursor
Opaque cursor token returned by the previous call; null/undefined for first page
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
trace_id
Unique identifier of the trace
Clarify units, where to obtain this value, or conventions not already expressed in the schema.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema42/100
Describe the returned fields so an agent can interpret the result.
The title clearly communicates the tool’s action and subject. Keep it concise.
Description76/100
Search OpenTelemetry logs with free text and the shared telemetry filter dialect, or run an OQL `fetch logs` pipeline. Results are newest first and cursor-paginated.
Describe the returned information so the agent knows whether it will answer the request.
Inputs70/100
8 of 10 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
from
Inclusive range start as an ISO 8601 timestamp.
Clear enough to supply this argument.
to
Exclusive range end as an ISO 8601 timestamp.
Clear enough to supply this argument.
query
Case-insensitive free-text search against the log body.
Clear enough to supply this argument.
filter_operator
How to combine structured filters.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
filters › items › field
Queryable log field, including dynamic attribute.*, resource.*, or scope.* fields.
Clear enough to supply this argument.
filters › items › op
Filter operator from the shared telemetry filter dialect.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
filters › items › values
String-encoded filter operands. exists and not_exists take no values; between takes two.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
oql
Optional OQL `fetch logs` pipeline. Do not combine with query or filters.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
limit
Not provided
Missing description. Explain what this value means and how to supply it.
page_token
Not provided
Missing description. Explain what this value means and how to supply it.
The title clearly communicates the tool’s action and subject. Keep it concise.
Description90/100
Get a quick workspace analytics snapshot: total requests, cost, tokens, errors, error rate, average latency, and top 5 models. Zero-config entry point for understanding workspace usage.
The description explains the capability, when to use it, and what to expect.
Inputs75/100
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
period
Time period for the overview.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema0/100
No output schema is declared. Add one for structured results so clients can interpret returned fields.
Not declared
Original tool metadata
{
"name": "get_analytics_overview",
"title": "Analytics Overview",
"description": "Get a quick workspace analytics snapshot: total requests, cost, tokens, errors, error rate, average latency, and top 5 models. Zero-config entry point for understanding workspace usage.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"period": {
"enum": [
"1h",
"6h",
"24h",
"7d",
"30d"
],
"type": "string",
"default": "24h",
"description": "Time period for the overview."
}
},
"additionalProperties": false
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description78/100
Flexible drill-down into workspace analytics. Query usage, cost, latency, errors, agent, or model performance metrics from pre-aggregated rollup tables. Supports time ranges, grouping, filtering, and granularity control.
The description explains the capability, when to use it, and what to expect.
Inputs43/100
6 of 11 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
metric
The metric category to query.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
time_range › start
Start time as ISO timestamp or relative shorthand (e.g. "24h", "7d", "30d").
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
time_range › end
End time as ISO timestamp. Defaults to now if omitted.
Clear enough to supply this argument.
group_by
Dimensions to group results by. Not all dimensions are available for all metrics.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
filters › provider
Not provided
Missing description. Explain what this value means and how to supply it.
filters › model
Not provided
Missing description. Explain what this value means and how to supply it.
filters › project_id
Not provided
Missing description. Explain what this value means and how to supply it.
filters › agent_name
Not provided
Missing description. Explain what this value means and how to supply it.
filters › http_status_code
Not provided
Missing description. Explain what this value means and how to supply it.
granularity
Time bucket granularity. "auto" prefers ≤6h→1m, ≤48h→1h, >48h→1d. For model usage metrics, it selects a retained granularity; explicit granularities outside retention are rejected.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
limit
Maximum number of data rows to return.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema0/100
No output schema is declared. Add one for structured results so clients can interpret returned fields.
Not declared
Original tool metadata
{
"name": "query_analytics",
"title": "Query Analytics",
"description": "Flexible drill-down into workspace analytics. Query usage, cost, latency, errors, agent, or model performance metrics from pre-aggregated rollup tables. Supports time ranges, grouping, filtering, and granularity control.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"metric",
"time_range"
],
"properties": {
"limit": {
"type": "number",
"default": 20,
"maximum": 100,
"minimum": 1,
"description": "Maximum number of data rows to return."
},
"metric": {
"enum": [
"usage",
"cost",
"latency",
"errors",
"agents",
"model_performance"
],
"type": "string",
"description": "The metric category to query."
},
"filters": {
"type": "object",
"properties": {
"model": {
"type": "string"
},
"provider": {
"type": "string"
},
"agent_name": {
"type": "string"
},
"project_id": {
"type": "string"
},
"http_status_code": {
"type": "string"
}
},
"description": "Filter conditions to narrow results.",
"additionalProperties": false
},
"group_by": {
"type": "array",
"items": {
"enum": [
"provider",
"model",
"project_id",
"http_status_code",
"agent_name"
],
"type": "string"
},
"description": "Dimensions to group results by. Not all dimensions are available for all metrics."
},
"time_range": {
"type": "object",
"required": [
"start"
],
"properties": {
"end": {
"type": "string",
"description": "End time as ISO timestamp. Defaults to now if omitted."
},
"start": {
"type": "string",
"description": "Start time as ISO timestamp or relative shorthand (e.g. \"24h\", \"7d\", \"30d\")."
}
},
"description": "Time range for the query.",
"additionalProperties": false
},
"granularity": {
"enum": [
"auto",
"1m",
"1h",
"1d"
],
"type": "string",
"default": "auto",
"description": "Time bucket granularity. \"auto\" prefers ≤6h→1m, ≤48h→1h, >48h→1d. For model usage metrics, it selects a retained granularity; explicit granularities outside retention are rejected."
}
},
"additionalProperties": false
}
}
Missing description. Explain what this value means and how to supply it.
input › anyOf › 1 › items › anyOf › 1 › type
Not provided
Missing description. Explain what this value means and how to supply it.
input › anyOf › 1 › items › anyOf › 1 › call_id
Not provided
Missing description. Explain what this value means and how to supply it.
input › anyOf › 1 › items › anyOf › 1 › output
Not provided
Missing description. Explain what this value means and how to supply it.
tools › items › type
Not provided
Missing description. Explain what this value means and how to supply it.
tools › items › name
Not provided
Missing description. Explain what this value means and how to supply it.
tools › items › description
Not provided
Missing description. Explain what this value means and how to supply it.
tools › items › parameters
Not provided
Missing description. Explain what this value means and how to supply it.
tools › items › strict
Not provided
Missing description. Explain what this value means and how to supply it.
metadata
Set of key-value pairs (max 16). Keys ≤64 chars, values ≤512 chars.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
background
Whether to run the request in the background and return immediately.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
variables
Template variables for dynamic content substitution in agent prompts.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
previous_response_id
The ID of a previous response to continue a multi-turn conversation.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema89/100
The output schema explains the structured result.
View output schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id",
"object",
"created_at",
"completed_at",
"status",
"incomplete_details",
"model",
"previous_response_id",
"instructions",
"output",
"error",
"tools",
"truncation",
"parallel_tool_calls",
"text",
"top_p",
"presence_penalty",
"frequency_penalty",
"top_logprobs",
"temperature",
"reasoning",
"usage",
"max_output_tokens",
"max_tool_calls",
"store",
"background",
"service_tier",
"metadata",
"safety_identifier",
"prompt_cache_key",
"prompt_cache_retention",
"input",
"user"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the response that was created."
},
"text": {
"allOf": [
{
"type": "object",
"required": [
"format"
],
"properties": {
"format": {
"anyOf": [
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"json_object"
],
"type": "string",
"default": "json_object"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"name",
"description",
"schema",
"strict"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"json_schema"
],
"type": "string",
"default": "json_schema"
},
"schema": {
"type": "object",
"properties": {},
"additionalProperties": {}
},
"strict": {
"type": "boolean"
},
"description": {
"type": [
"string",
"null"
]
}
},
"additionalProperties": false
}
]
},
"verbosity": {
"enum": [
"low",
"medium",
"high"
],
"type": "string"
}
},
"additionalProperties": false
},
{}
]
},
"user": {
"type": [
"string",
"null"
]
},
"error": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"code",
"message"
],
"properties": {
"code": {
"type": "string",
"description": "A machine-readable error code that was returned."
},
"message": {
"type": "string",
"description": "A human-readable description of the error that was returned."
}
},
"description": "An error that occurred while generating the response.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"input": {
"type": "array",
"items": {},
"description": "Array of input items (messages, function call outputs, etc.)."
},
"model": {
"type": "string",
"description": "The model that generated this response."
},
"store": {
"type": "boolean",
"description": "Whether this response was stored so it can be retrieved later."
},
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"name",
"description",
"parameters",
"strict"
],
"properties": {
"name": {
"type": "string",
"description": "The name of the function to call."
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function",
"description": "The type of the function tool. Always `function`."
},
"strict": {
"type": [
"boolean",
"null"
]
},
"parameters": {
"anyOf": [
{
"type": "object",
"properties": {},
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"description": {
"type": [
"string",
"null"
]
}
},
"description": "A tool that can be used to generate a response.",
"additionalProperties": false
},
"description": "The tools that were available to the model during response generation."
},
"top_p": {
"type": "number",
"description": "The nucleus sampling parameter that was used for this response."
},
"usage": {
"anyOf": [
{
"type": "object",
"required": [
"input_tokens",
"output_tokens",
"total_tokens",
"input_tokens_details",
"output_tokens_details"
],
"properties": {
"input_cost": {
"type": "number",
"description": "Cost (USD) of input tokens. Present when billing was computed for this response."
},
"total_cost": {
"type": "number",
"description": "Total cost (USD) of the response. Present when billing was computed for this response."
},
"output_cost": {
"type": "number",
"description": "Cost (USD) of output tokens. Present when billing was computed for this response."
},
"input_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were used to generate the response."
},
"total_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The total number of tokens that were used."
},
"output_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of output tokens that were generated by the model."
},
"web_search_requests": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Number of web search tool invocations performed during the response."
},
"input_tokens_details": {
"type": "object",
"required": [
"cached_tokens"
],
"properties": {
"cached_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were served from cache."
},
"cache_creation_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were used to create a new cache entry (Anthropic prompt caching)."
},
"cache_creation_1h_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of cache_creation_tokens written to the 1-hour TTL cache (Anthropic prompt caching)."
},
"cache_creation_5m_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of cache_creation_tokens written to the 5-minute TTL cache (Anthropic prompt caching)."
}
},
"description": "A breakdown of input token usage that was recorded.",
"additionalProperties": {}
},
"output_tokens_details": {
"type": "object",
"required": [
"reasoning_tokens"
],
"properties": {
"reasoning_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of output tokens that were attributed to reasoning."
}
},
"description": "A breakdown of output token usage that was recorded.",
"additionalProperties": {}
}
},
"description": "Token usage statistics that were recorded for the response.",
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"entity": {
"type": "object",
"required": [
"type",
"id",
"key"
],
"properties": {
"id": {
"type": "string"
},
"key": {
"type": "string"
},
"type": {
"type": "string"
}
},
"description": "Entity (e.g. agent) that produced this response.",
"additionalProperties": false
},
"memory": {
"anyOf": [
{},
{
"type": "null"
}
],
"description": "orq.ai memory store reference attached to this response."
},
"object": {
"enum": [
"response"
],
"type": "string",
"default": "response",
"description": "The object type, which was always `response`."
},
"output": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"id",
"status",
"role",
"content"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the message."
},
"role": {
"allOf": [
{
"enum": [
"user",
"assistant",
"system",
"developer"
],
"type": "string"
},
{}
]
},
"type": {
"enum": [
"message"
],
"type": "string",
"default": "message",
"description": "The type of the message. Always set to `message`."
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string"
},
{}
]
},
"content": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"video_url"
],
"properties": {
"type": {
"enum": [
"input_video"
],
"type": "string",
"description": "The type of the input content. Always `input_video`."
},
"video_url": {
"type": "string",
"description": "A base64 or remote url that resolves to a video file."
}
},
"description": "A content block representing a video input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The content of the message"
}
},
"description": "A message to or from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"call_id",
"name",
"arguments",
"status"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the function call item."
},
"name": {
"type": "string",
"description": "The name of the function that was called."
},
"type": {
"enum": [
"function_call"
],
"type": "string",
"default": "function_call",
"description": "The type of the item. Always `function_call`."
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string"
},
{}
]
},
"call_id": {
"type": "string",
"description": "The unique ID of the function tool call that was generated."
},
"arguments": {
"type": "string",
"description": "The arguments JSON string that was generated."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
}
},
"description": "A function tool call that was generated by the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"call_id",
"output",
"status"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the function tool call output. Populated when this item is returned via API."
},
"type": {
"enum": [
"function_call_output"
],
"type": "string",
"default": "function_call_output",
"description": "The type of the function tool call output. Always `function_call_output`."
},
"output": {
"anyOf": [
{
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
}
},
{
"type": "string"
}
]
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string",
"description": "Similar to `FunctionCallStatus`. All three options are allowed here for compatibility, but because in practice these items will be provided by developers, only `completed` should be used."
},
{}
]
},
"call_id": {
"type": "string",
"description": "The unique ID of the function tool call generated by the model."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
}
},
"description": "A function tool call output that was returned by the tool.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"summary"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the reasoning item."
},
"type": {
"enum": [
"reasoning"
],
"type": "string",
"default": "reasoning",
"description": "The type of the item. Always `reasoning`."
},
"content": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The reasoning content that was generated."
},
"summary": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The reasoning summary content that was generated."
},
"signature": {
"type": "string",
"description": "The signature of the reasoning content that was generated."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
},
"encrypted_content": {
"type": "string",
"description": "The encrypted reasoning content that was generated."
}
},
"description": "A reasoning item that was generated by the model.",
"additionalProperties": false
},
{
"allOf": [
{
"type": "object",
"required": [
"id",
"type",
"status",
"result"
],
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"result": {},
"status": {
"type": "string"
}
},
"additionalProperties": false
},
{}
]
}
],
"description": "An item representing a message, tool call, tool output, reasoning, or other response element."
},
"description": "The output items that were generated by the model."
},
"status": {
"type": "string",
"description": "The status that was set for the response."
},
"metadata": {
"description": "Developer-defined metadata that was associated with the response."
},
"reasoning": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"effort",
"summary"
],
"properties": {
"effort": {
"anyOf": [
{
"enum": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
],
"type": "string"
},
{
"type": "null"
}
]
},
"summary": {
"anyOf": [
{
"allOf": [
{
"enum": [
"concise",
"detailed",
"auto"
],
"type": "string"
},
{}
]
},
{
"type": "null"
}
]
}
},
"description": "Reasoning configuration and metadata that were used for the response.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"telemetry": {
"type": "object",
"required": [
"trace_id",
"span_id"
],
"properties": {
"span_id": {
"type": "string"
},
"trace_id": {
"type": "string"
}
},
"description": "OpenTelemetry identifiers for this response.",
"additionalProperties": false
},
"variables": {
"type": "object",
"description": "Template variables that were applied when rendering this response.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"background": {
"type": "boolean",
"description": "Whether this request was run in the background."
},
"created_at": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The Unix timestamp (in seconds) for when the response was created."
},
"project_id": {
"type": [
"string",
"null"
],
"description": "Project ID associated with the entity that produced this response."
},
"truncation": {
"allOf": [
{
"enum": [
"auto",
"disabled"
],
"type": "string"
},
{}
]
},
"output_text": {
"type": "string",
"description": "Convenience field aggregating text from output items. Added by the OpenAI SDK on parse."
},
"temperature": {
"type": "number",
"description": "The sampling temperature that was used for this response."
},
"tool_choice": {
"anyOf": [
{
"type": "object",
"required": [
"type"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function"
}
},
"additionalProperties": false
},
{
"enum": [
"none",
"auto",
"required"
],
"type": "string"
},
{
"type": "object",
"required": [
"type",
"tools",
"mode"
],
"properties": {
"mode": {
"enum": [
"none",
"auto",
"required"
],
"type": "string"
},
"type": {
"enum": [
"allowed_tools"
],
"type": "string",
"default": "allowed_tools"
},
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"type"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function"
}
},
"additionalProperties": false
}
}
},
"additionalProperties": false
}
]
},
"completed_at": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"conversation": {
"anyOf": [
{},
{
"type": "null"
}
],
"description": "orq.ai conversation context attached to this response."
},
"instructions": {
"type": [
"string",
"null"
]
},
"service_tier": {
"type": "string",
"description": "The service tier that was used for this response."
},
"top_logprobs": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of most likely tokens that were returned at each position, along with their log probabilities."
},
"max_tool_calls": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"presence_penalty": {
"type": "number",
"description": "The presence penalty that was used to penalize new tokens based on whether they appear in the text so far."
},
"prompt_cache_key": {
"type": [
"string",
"null"
]
},
"frequency_penalty": {
"type": "number",
"description": "The frequency penalty that was used to penalize new tokens based on their frequency in the text so far."
},
"max_output_tokens": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"safety_identifier": {
"type": [
"string",
"null"
]
},
"incomplete_details": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"reason"
],
"properties": {
"reason": {
"type": "string",
"description": "The reason the response could not be completed."
}
},
"description": "Details about why the response was incomplete.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"parallel_tool_calls": {
"type": "boolean",
"description": "Whether the model was allowed to call multiple tools in parallel."
},
"previous_response_id": {
"type": [
"string",
"null"
]
},
"prompt_cache_retention": {
"type": [
"string",
"null"
]
}
},
"description": "The complete response object that was returned by the Responses API.",
"additionalProperties": {}
}
Original tool metadata
{
"name": "invoke_agent",
"title": "Invoke Agent",
"description": "Invoke an agent using the Responses API. The model param must follow the format \"agent/{agent_key}\". Returns the full response resource.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"model"
],
"properties": {
"input": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"role",
"content"
],
"properties": {
"role": {
"enum": [
"user",
"system",
"assistant",
"developer"
],
"type": "string"
},
"content": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"type": "string",
"const": "input_text"
}
}
}
}
]
}
}
},
{
"type": "object",
"required": [
"type",
"call_id",
"output"
],
"properties": {
"type": {
"type": "string",
"const": "function_call_output"
},
"output": {
"type": "string"
},
"call_id": {
"type": "string",
"minLength": 1
}
}
}
]
}
}
],
"description": "The input to send to the agent. Can be a string or an array of input items."
},
"model": {
"type": "string",
"minLength": 1,
"description": "The model to use in the format \"agent/{agent_key}\" (e.g. \"agent/my-support-agent\")."
},
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"pattern": "^[a-zA-Z0-9_-]+$",
"maxLength": 64,
"minLength": 1
},
"type": {
"type": "string",
"const": "function",
"default": "function"
},
"strict": {
"type": "boolean"
},
"parameters": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"description": {
"type": "string"
}
}
},
"description": "Function tools available to the agent."
},
"metadata": {
"type": "object",
"description": "Set of key-value pairs (max 16). Keys ≤64 chars, values ≤512 chars.",
"propertyNames": {
"type": "string",
"maxLength": 64
},
"additionalProperties": {
"type": "string",
"maxLength": 512
}
},
"variables": {
"type": "object",
"description": "Template variables for dynamic content substitution in agent prompts.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"background": {
"type": "boolean",
"description": "Whether to run the request in the background and return immediately."
},
"previous_response_id": {
"type": "string",
"description": "The ID of a previous response to continue a multi-turn conversation."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id",
"object",
"created_at",
"completed_at",
"status",
"incomplete_details",
"model",
"previous_response_id",
"instructions",
"output",
"error",
"tools",
"truncation",
"parallel_tool_calls",
"text",
"top_p",
"presence_penalty",
"frequency_penalty",
"top_logprobs",
"temperature",
"reasoning",
"usage",
"max_output_tokens",
"max_tool_calls",
"store",
"background",
"service_tier",
"metadata",
"safety_identifier",
"prompt_cache_key",
"prompt_cache_retention",
"input",
"user"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the response that was created."
},
"text": {
"allOf": [
{
"type": "object",
"required": [
"format"
],
"properties": {
"format": {
"anyOf": [
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"json_object"
],
"type": "string",
"default": "json_object"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"name",
"description",
"schema",
"strict"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"json_schema"
],
"type": "string",
"default": "json_schema"
},
"schema": {
"type": "object",
"properties": {},
"additionalProperties": {}
},
"strict": {
"type": "boolean"
},
"description": {
"type": [
"string",
"null"
]
}
},
"additionalProperties": false
}
]
},
"verbosity": {
"enum": [
"low",
"medium",
"high"
],
"type": "string"
}
},
"additionalProperties": false
},
{}
]
},
"user": {
"type": [
"string",
"null"
]
},
"error": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"code",
"message"
],
"properties": {
"code": {
"type": "string",
"description": "A machine-readable error code that was returned."
},
"message": {
"type": "string",
"description": "A human-readable description of the error that was returned."
}
},
"description": "An error that occurred while generating the response.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"input": {
"type": "array",
"items": {},
"description": "Array of input items (messages, function call outputs, etc.)."
},
"model": {
"type": "string",
"description": "The model that generated this response."
},
"store": {
"type": "boolean",
"description": "Whether this response was stored so it can be retrieved later."
},
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"name",
"description",
"parameters",
"strict"
],
"properties": {
"name": {
"type": "string",
"description": "The name of the function to call."
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function",
"description": "The type of the function tool. Always `function`."
},
"strict": {
"type": [
"boolean",
"null"
]
},
"parameters": {
"anyOf": [
{
"type": "object",
"properties": {},
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"description": {
"type": [
"string",
"null"
]
}
},
"description": "A tool that can be used to generate a response.",
"additionalProperties": false
},
"description": "The tools that were available to the model during response generation."
},
"top_p": {
"type": "number",
"description": "The nucleus sampling parameter that was used for this response."
},
"usage": {
"anyOf": [
{
"type": "object",
"required": [
"input_tokens",
"output_tokens",
"total_tokens",
"input_tokens_details",
"output_tokens_details"
],
"properties": {
"input_cost": {
"type": "number",
"description": "Cost (USD) of input tokens. Present when billing was computed for this response."
},
"total_cost": {
"type": "number",
"description": "Total cost (USD) of the response. Present when billing was computed for this response."
},
"output_cost": {
"type": "number",
"description": "Cost (USD) of output tokens. Present when billing was computed for this response."
},
"input_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were used to generate the response."
},
"total_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The total number of tokens that were used."
},
"output_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of output tokens that were generated by the model."
},
"web_search_requests": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Number of web search tool invocations performed during the response."
},
"input_tokens_details": {
"type": "object",
"required": [
"cached_tokens"
],
"properties": {
"cached_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were served from cache."
},
"cache_creation_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were used to create a new cache entry (Anthropic prompt caching)."
},
"cache_creation_1h_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of cache_creation_tokens written to the 1-hour TTL cache (Anthropic prompt caching)."
},
"cache_creation_5m_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of cache_creation_tokens written to the 5-minute TTL cache (Anthropic prompt caching)."
}
},
"description": "A breakdown of input token usage that was recorded.",
"additionalProperties": {}
},
"output_tokens_details": {
"type": "object",
"required": [
"reasoning_tokens"
],
"properties": {
"reasoning_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of output tokens that were attributed to reasoning."
}
},
"description": "A breakdown of output token usage that was recorded.",
"additionalProperties": {}
}
},
"description": "Token usage statistics that were recorded for the response.",
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"entity": {
"type": "object",
"required": [
"type",
"id",
"key"
],
"properties": {
"id": {
"type": "string"
},
"key": {
"type": "string"
},
"type": {
"type": "string"
}
},
"description": "Entity (e.g. agent) that produced this response.",
"additionalProperties": false
},
"memory": {
"anyOf": [
{},
{
"type": "null"
}
],
"description": "orq.ai memory store reference attached to this response."
},
"object": {
"enum": [
"response"
],
"type": "string",
"default": "response",
"description": "The object type, which was always `response`."
},
"output": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"id",
"status",
"role",
"content"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the message."
},
"role": {
"allOf": [
{
"enum": [
"user",
"assistant",
"system",
"developer"
],
"type": "string"
},
{}
]
},
"type": {
"enum": [
"message"
],
"type": "string",
"default": "message",
"description": "The type of the message. Always set to `message`."
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string"
},
{}
]
},
"content": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"video_url"
],
"properties": {
"type": {
"enum": [
"input_video"
],
"type": "string",
"description": "The type of the input content. Always `input_video`."
},
"video_url": {
"type": "string",
"description": "A base64 or remote url that resolves to a video file."
}
},
"description": "A content block representing a video input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The content of the message"
}
},
"description": "A message to or from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"call_id",
"name",
"arguments",
"status"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the function call item."
},
"name": {
"type": "string",
"description": "The name of the function that was called."
},
"type": {
"enum": [
"function_call"
],
"type": "string",
"default": "function_call",
"description": "The type of the item. Always `function_call`."
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string"
},
{}
]
},
"call_id": {
"type": "string",
"description": "The unique ID of the function tool call that was generated."
},
"arguments": {
"type": "string",
"description": "The arguments JSON string that was generated."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
}
},
"description": "A function tool call that was generated by the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"call_id",
"output",
"status"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the function tool call output. Populated when this item is returned via API."
},
"type": {
"enum": [
"function_call_output"
],
"type": "string",
"default": "function_call_output",
"description": "The type of the function tool call output. Always `function_call_output`."
},
"output": {
"anyOf": [
{
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
}
},
{
"type": "string"
}
]
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string",
"description": "Similar to `FunctionCallStatus`. All three options are allowed here for compatibility, but because in practice these items will be provided by developers, only `completed` should be used."
},
{}
]
},
"call_id": {
"type": "string",
"description": "The unique ID of the function tool call generated by the model."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
}
},
"description": "A function tool call output that was returned by the tool.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"summary"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the reasoning item."
},
"type": {
"enum": [
"reasoning"
],
"type": "string",
"default": "reasoning",
"description": "The type of the item. Always `reasoning`."
},
"content": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The reasoning content that was generated."
},
"summary": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The reasoning summary content that was generated."
},
"signature": {
"type": "string",
"description": "The signature of the reasoning content that was generated."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
},
"encrypted_content": {
"type": "string",
"description": "The encrypted reasoning content that was generated."
}
},
"description": "A reasoning item that was generated by the model.",
"additionalProperties": false
},
{
"allOf": [
{
"type": "object",
"required": [
"id",
"type",
"status",
"result"
],
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"result": {},
"status": {
"type": "string"
}
},
"additionalProperties": false
},
{}
]
}
],
"description": "An item representing a message, tool call, tool output, reasoning, or other response element."
},
"description": "The output items that were generated by the model."
},
"status": {
"type": "string",
"description": "The status that was set for the response."
},
"metadata": {
"description": "Developer-defined metadata that was associated with the response."
},
"reasoning": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"effort",
"summary"
],
"properties": {
"effort": {
"anyOf": [
{
"enum": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
],
"type": "string"
},
{
"type": "null"
}
]
},
"summary": {
"anyOf": [
{
"allOf": [
{
"enum": [
"concise",
"detailed",
"auto"
],
"type": "string"
},
{}
]
},
{
"type": "null"
}
]
}
},
"description": "Reasoning configuration and metadata that were used for the response.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"telemetry": {
"type": "object",
"required": [
"trace_id",
"span_id"
],
"properties": {
"span_id": {
"type": "string"
},
"trace_id": {
"type": "string"
}
},
"description": "OpenTelemetry identifiers for this response.",
"additionalProperties": false
},
"variables": {
"type": "object",
"description": "Template variables that were applied when rendering this response.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"background": {
"type": "boolean",
"description": "Whether this request was run in the background."
},
"created_at": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The Unix timestamp (in seconds) for when the response was created."
},
"project_id": {
"type": [
"string",
"null"
],
"description": "Project ID associated with the entity that produced this response."
},
"truncation": {
"allOf": [
{
"enum": [
"auto",
"disabled"
],
"type": "string"
},
{}
]
},
"output_text": {
"type": "string",
"description": "Convenience field aggregating text from output items. Added by the OpenAI SDK on parse."
},
"temperature": {
"type": "number",
"description": "The sampling temperature that was used for this response."
},
"tool_choice": {
"anyOf": [
{
"type": "object",
"required": [
"type"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function"
}
},
"additionalProperties": false
},
{
"enum": [
"none",
"auto",
"required"
],
"type": "string"
},
{
"type": "object",
"required": [
"type",
"tools",
"mode"
],
"properties": {
"mode": {
"enum": [
"none",
"auto",
"required"
],
"type": "string"
},
"type": {
"enum": [
"allowed_tools"
],
"type": "string",
"default": "allowed_tools"
},
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"type"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function"
}
},
"additionalProperties": false
}
}
},
"additionalProperties": false
}
]
},
"completed_at": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"conversation": {
"anyOf": [
{},
{
"type": "null"
}
],
"description": "orq.ai conversation context attached to this response."
},
"instructions": {
"type": [
"string",
"null"
]
},
"service_tier": {
"type": "string",
"description": "The service tier that was used for this response."
},
"top_logprobs": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of most likely tokens that were returned at each position, along with their log probabilities."
},
"max_tool_calls": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"presence_penalty": {
"type": "number",
"description": "The presence penalty that was used to penalize new tokens based on whether they appear in the text so far."
},
"prompt_cache_key": {
"type": [
"string",
"null"
]
},
"frequency_penalty": {
"type": "number",
"description": "The frequency penalty that was used to penalize new tokens based on their frequency in the text so far."
},
"max_output_tokens": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"safety_identifier": {
"type": [
"string",
"null"
]
},
"incomplete_details": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"reason"
],
"properties": {
"reason": {
"type": "string",
"description": "The reason the response could not be completed."
}
},
"description": "Details about why the response was incomplete.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"parallel_tool_calls": {
"type": "boolean",
"description": "Whether the model was allowed to call multiple tools in parallel."
},
"previous_response_id": {
"type": [
"string",
"null"
]
},
"prompt_cache_retention": {
"type": [
"string",
"null"
]
}
},
"description": "The complete response object that was returned by the Responses API.",
"additionalProperties": {}
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description88/100
Retrieve a previously created agent response by its ID. Returns the full response resource including output, usage, and status.
The description explains the capability, when to use it, and what to expect.
Inputs75/100
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
response_id
The ID of the response to retrieve (e.g. "resp_...")
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
Not declared
Output schema86/100
The output schema explains the structured result.
View output schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id",
"object",
"created_at",
"completed_at",
"status",
"incomplete_details",
"model",
"previous_response_id",
"instructions",
"output",
"error",
"tools",
"truncation",
"parallel_tool_calls",
"text",
"top_p",
"presence_penalty",
"frequency_penalty",
"top_logprobs",
"temperature",
"reasoning",
"usage",
"max_output_tokens",
"max_tool_calls",
"store",
"background",
"service_tier",
"metadata",
"safety_identifier",
"prompt_cache_key",
"prompt_cache_retention",
"input",
"user"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the response that was created."
},
"text": {
"allOf": [
{
"type": "object",
"required": [
"format"
],
"properties": {
"format": {
"anyOf": [
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"json_object"
],
"type": "string",
"default": "json_object"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"name",
"description",
"schema",
"strict"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"json_schema"
],
"type": "string",
"default": "json_schema"
},
"schema": {
"type": "object",
"properties": {},
"additionalProperties": {}
},
"strict": {
"type": "boolean"
},
"description": {
"type": [
"string",
"null"
]
}
},
"additionalProperties": false
}
]
},
"verbosity": {
"enum": [
"low",
"medium",
"high"
],
"type": "string"
}
},
"additionalProperties": false
},
{}
]
},
"user": {
"type": [
"string",
"null"
]
},
"error": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"code",
"message"
],
"properties": {
"code": {
"type": "string",
"description": "A machine-readable error code that was returned."
},
"message": {
"type": "string",
"description": "A human-readable description of the error that was returned."
}
},
"description": "An error that occurred while generating the response.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"input": {
"type": "array",
"items": {},
"description": "Array of input items (messages, function call outputs, etc.)."
},
"model": {
"type": "string",
"description": "The model that generated this response."
},
"store": {
"type": "boolean",
"description": "Whether this response was stored so it can be retrieved later."
},
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"name",
"description",
"parameters",
"strict"
],
"properties": {
"name": {
"type": "string",
"description": "The name of the function to call."
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function",
"description": "The type of the function tool. Always `function`."
},
"strict": {
"type": [
"boolean",
"null"
]
},
"parameters": {
"anyOf": [
{
"type": "object",
"properties": {},
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"description": {
"type": [
"string",
"null"
]
}
},
"description": "A tool that can be used to generate a response.",
"additionalProperties": false
},
"description": "The tools that were available to the model during response generation."
},
"top_p": {
"type": "number",
"description": "The nucleus sampling parameter that was used for this response."
},
"usage": {
"anyOf": [
{
"type": "object",
"required": [
"input_tokens",
"output_tokens",
"total_tokens",
"input_tokens_details",
"output_tokens_details"
],
"properties": {
"input_cost": {
"type": "number",
"description": "Cost (USD) of input tokens. Present when billing was computed for this response."
},
"total_cost": {
"type": "number",
"description": "Total cost (USD) of the response. Present when billing was computed for this response."
},
"output_cost": {
"type": "number",
"description": "Cost (USD) of output tokens. Present when billing was computed for this response."
},
"input_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were used to generate the response."
},
"total_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The total number of tokens that were used."
},
"output_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of output tokens that were generated by the model."
},
"web_search_requests": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Number of web search tool invocations performed during the response."
},
"input_tokens_details": {
"type": "object",
"required": [
"cached_tokens"
],
"properties": {
"cached_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were served from cache."
},
"cache_creation_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were used to create a new cache entry (Anthropic prompt caching)."
},
"cache_creation_1h_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of cache_creation_tokens written to the 1-hour TTL cache (Anthropic prompt caching)."
},
"cache_creation_5m_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of cache_creation_tokens written to the 5-minute TTL cache (Anthropic prompt caching)."
}
},
"description": "A breakdown of input token usage that was recorded.",
"additionalProperties": {}
},
"output_tokens_details": {
"type": "object",
"required": [
"reasoning_tokens"
],
"properties": {
"reasoning_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of output tokens that were attributed to reasoning."
}
},
"description": "A breakdown of output token usage that was recorded.",
"additionalProperties": {}
}
},
"description": "Token usage statistics that were recorded for the response.",
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"entity": {
"type": "object",
"required": [
"type",
"id",
"key"
],
"properties": {
"id": {
"type": "string"
},
"key": {
"type": "string"
},
"type": {
"type": "string"
}
},
"description": "Entity (e.g. agent) that produced this response.",
"additionalProperties": false
},
"memory": {
"anyOf": [
{},
{
"type": "null"
}
],
"description": "orq.ai memory store reference attached to this response."
},
"object": {
"enum": [
"response"
],
"type": "string",
"default": "response",
"description": "The object type, which was always `response`."
},
"output": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"id",
"status",
"role",
"content"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the message."
},
"role": {
"allOf": [
{
"enum": [
"user",
"assistant",
"system",
"developer"
],
"type": "string"
},
{}
]
},
"type": {
"enum": [
"message"
],
"type": "string",
"default": "message",
"description": "The type of the message. Always set to `message`."
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string"
},
{}
]
},
"content": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"video_url"
],
"properties": {
"type": {
"enum": [
"input_video"
],
"type": "string",
"description": "The type of the input content. Always `input_video`."
},
"video_url": {
"type": "string",
"description": "A base64 or remote url that resolves to a video file."
}
},
"description": "A content block representing a video input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The content of the message"
}
},
"description": "A message to or from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"call_id",
"name",
"arguments",
"status"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the function call item."
},
"name": {
"type": "string",
"description": "The name of the function that was called."
},
"type": {
"enum": [
"function_call"
],
"type": "string",
"default": "function_call",
"description": "The type of the item. Always `function_call`."
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string"
},
{}
]
},
"call_id": {
"type": "string",
"description": "The unique ID of the function tool call that was generated."
},
"arguments": {
"type": "string",
"description": "The arguments JSON string that was generated."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
}
},
"description": "A function tool call that was generated by the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"call_id",
"output",
"status"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the function tool call output. Populated when this item is returned via API."
},
"type": {
"enum": [
"function_call_output"
],
"type": "string",
"default": "function_call_output",
"description": "The type of the function tool call output. Always `function_call_output`."
},
"output": {
"anyOf": [
{
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
}
},
{
"type": "string"
}
]
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string",
"description": "Similar to `FunctionCallStatus`. All three options are allowed here for compatibility, but because in practice these items will be provided by developers, only `completed` should be used."
},
{}
]
},
"call_id": {
"type": "string",
"description": "The unique ID of the function tool call generated by the model."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
}
},
"description": "A function tool call output that was returned by the tool.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"summary"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the reasoning item."
},
"type": {
"enum": [
"reasoning"
],
"type": "string",
"default": "reasoning",
"description": "The type of the item. Always `reasoning`."
},
"content": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The reasoning content that was generated."
},
"summary": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The reasoning summary content that was generated."
},
"signature": {
"type": "string",
"description": "The signature of the reasoning content that was generated."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
},
"encrypted_content": {
"type": "string",
"description": "The encrypted reasoning content that was generated."
}
},
"description": "A reasoning item that was generated by the model.",
"additionalProperties": false
},
{
"allOf": [
{
"type": "object",
"required": [
"id",
"type",
"status",
"result"
],
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"result": {},
"status": {
"type": "string"
}
},
"additionalProperties": false
},
{}
]
}
],
"description": "An item representing a message, tool call, tool output, reasoning, or other response element."
},
"description": "The output items that were generated by the model."
},
"status": {
"type": "string",
"description": "The status that was set for the response."
},
"metadata": {
"description": "Developer-defined metadata that was associated with the response."
},
"reasoning": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"effort",
"summary"
],
"properties": {
"effort": {
"anyOf": [
{
"enum": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
],
"type": "string"
},
{
"type": "null"
}
]
},
"summary": {
"anyOf": [
{
"allOf": [
{
"enum": [
"concise",
"detailed",
"auto"
],
"type": "string"
},
{}
]
},
{
"type": "null"
}
]
}
},
"description": "Reasoning configuration and metadata that were used for the response.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"telemetry": {
"type": "object",
"required": [
"trace_id",
"span_id"
],
"properties": {
"span_id": {
"type": "string"
},
"trace_id": {
"type": "string"
}
},
"description": "OpenTelemetry identifiers for this response.",
"additionalProperties": false
},
"variables": {
"type": "object",
"description": "Template variables that were applied when rendering this response.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"background": {
"type": "boolean",
"description": "Whether this request was run in the background."
},
"created_at": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The Unix timestamp (in seconds) for when the response was created."
},
"project_id": {
"type": [
"string",
"null"
],
"description": "Project ID associated with the entity that produced this response."
},
"truncation": {
"allOf": [
{
"enum": [
"auto",
"disabled"
],
"type": "string"
},
{}
]
},
"output_text": {
"type": "string",
"description": "Convenience field aggregating text from output items. Added by the OpenAI SDK on parse."
},
"temperature": {
"type": "number",
"description": "The sampling temperature that was used for this response."
},
"tool_choice": {
"anyOf": [
{
"type": "object",
"required": [
"type"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function"
}
},
"additionalProperties": false
},
{
"enum": [
"none",
"auto",
"required"
],
"type": "string"
},
{
"type": "object",
"required": [
"type",
"tools",
"mode"
],
"properties": {
"mode": {
"enum": [
"none",
"auto",
"required"
],
"type": "string"
},
"type": {
"enum": [
"allowed_tools"
],
"type": "string",
"default": "allowed_tools"
},
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"type"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function"
}
},
"additionalProperties": false
}
}
},
"additionalProperties": false
}
]
},
"completed_at": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"conversation": {
"anyOf": [
{},
{
"type": "null"
}
],
"description": "orq.ai conversation context attached to this response."
},
"instructions": {
"type": [
"string",
"null"
]
},
"service_tier": {
"type": "string",
"description": "The service tier that was used for this response."
},
"top_logprobs": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of most likely tokens that were returned at each position, along with their log probabilities."
},
"max_tool_calls": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"presence_penalty": {
"type": "number",
"description": "The presence penalty that was used to penalize new tokens based on whether they appear in the text so far."
},
"prompt_cache_key": {
"type": [
"string",
"null"
]
},
"frequency_penalty": {
"type": "number",
"description": "The frequency penalty that was used to penalize new tokens based on their frequency in the text so far."
},
"max_output_tokens": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"safety_identifier": {
"type": [
"string",
"null"
]
},
"incomplete_details": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"reason"
],
"properties": {
"reason": {
"type": "string",
"description": "The reason the response could not be completed."
}
},
"description": "Details about why the response was incomplete.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"parallel_tool_calls": {
"type": "boolean",
"description": "Whether the model was allowed to call multiple tools in parallel."
},
"previous_response_id": {
"type": [
"string",
"null"
]
},
"prompt_cache_retention": {
"type": [
"string",
"null"
]
}
},
"description": "The complete response object that was returned by the Responses API.",
"additionalProperties": {}
}
Original tool metadata
{
"name": "retrieve_agent_response",
"title": "Retrieve Agent Response",
"description": "Retrieve a previously created agent response by its ID. Returns the full response resource including output, usage, and status.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"response_id"
],
"properties": {
"response_id": {
"type": "string",
"minLength": 1,
"description": "The ID of the response to retrieve (e.g. \"resp_...\")"
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id",
"object",
"created_at",
"completed_at",
"status",
"incomplete_details",
"model",
"previous_response_id",
"instructions",
"output",
"error",
"tools",
"truncation",
"parallel_tool_calls",
"text",
"top_p",
"presence_penalty",
"frequency_penalty",
"top_logprobs",
"temperature",
"reasoning",
"usage",
"max_output_tokens",
"max_tool_calls",
"store",
"background",
"service_tier",
"metadata",
"safety_identifier",
"prompt_cache_key",
"prompt_cache_retention",
"input",
"user"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the response that was created."
},
"text": {
"allOf": [
{
"type": "object",
"required": [
"format"
],
"properties": {
"format": {
"anyOf": [
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"json_object"
],
"type": "string",
"default": "json_object"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"name",
"description",
"schema",
"strict"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"json_schema"
],
"type": "string",
"default": "json_schema"
},
"schema": {
"type": "object",
"properties": {},
"additionalProperties": {}
},
"strict": {
"type": "boolean"
},
"description": {
"type": [
"string",
"null"
]
}
},
"additionalProperties": false
}
]
},
"verbosity": {
"enum": [
"low",
"medium",
"high"
],
"type": "string"
}
},
"additionalProperties": false
},
{}
]
},
"user": {
"type": [
"string",
"null"
]
},
"error": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"code",
"message"
],
"properties": {
"code": {
"type": "string",
"description": "A machine-readable error code that was returned."
},
"message": {
"type": "string",
"description": "A human-readable description of the error that was returned."
}
},
"description": "An error that occurred while generating the response.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"input": {
"type": "array",
"items": {},
"description": "Array of input items (messages, function call outputs, etc.)."
},
"model": {
"type": "string",
"description": "The model that generated this response."
},
"store": {
"type": "boolean",
"description": "Whether this response was stored so it can be retrieved later."
},
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"name",
"description",
"parameters",
"strict"
],
"properties": {
"name": {
"type": "string",
"description": "The name of the function to call."
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function",
"description": "The type of the function tool. Always `function`."
},
"strict": {
"type": [
"boolean",
"null"
]
},
"parameters": {
"anyOf": [
{
"type": "object",
"properties": {},
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"description": {
"type": [
"string",
"null"
]
}
},
"description": "A tool that can be used to generate a response.",
"additionalProperties": false
},
"description": "The tools that were available to the model during response generation."
},
"top_p": {
"type": "number",
"description": "The nucleus sampling parameter that was used for this response."
},
"usage": {
"anyOf": [
{
"type": "object",
"required": [
"input_tokens",
"output_tokens",
"total_tokens",
"input_tokens_details",
"output_tokens_details"
],
"properties": {
"input_cost": {
"type": "number",
"description": "Cost (USD) of input tokens. Present when billing was computed for this response."
},
"total_cost": {
"type": "number",
"description": "Total cost (USD) of the response. Present when billing was computed for this response."
},
"output_cost": {
"type": "number",
"description": "Cost (USD) of output tokens. Present when billing was computed for this response."
},
"input_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were used to generate the response."
},
"total_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The total number of tokens that were used."
},
"output_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of output tokens that were generated by the model."
},
"web_search_requests": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Number of web search tool invocations performed during the response."
},
"input_tokens_details": {
"type": "object",
"required": [
"cached_tokens"
],
"properties": {
"cached_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were served from cache."
},
"cache_creation_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of input tokens that were used to create a new cache entry (Anthropic prompt caching)."
},
"cache_creation_1h_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of cache_creation_tokens written to the 1-hour TTL cache (Anthropic prompt caching)."
},
"cache_creation_5m_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of cache_creation_tokens written to the 5-minute TTL cache (Anthropic prompt caching)."
}
},
"description": "A breakdown of input token usage that was recorded.",
"additionalProperties": {}
},
"output_tokens_details": {
"type": "object",
"required": [
"reasoning_tokens"
],
"properties": {
"reasoning_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of output tokens that were attributed to reasoning."
}
},
"description": "A breakdown of output token usage that was recorded.",
"additionalProperties": {}
}
},
"description": "Token usage statistics that were recorded for the response.",
"additionalProperties": {}
},
{
"type": "null"
}
]
},
"entity": {
"type": "object",
"required": [
"type",
"id",
"key"
],
"properties": {
"id": {
"type": "string"
},
"key": {
"type": "string"
},
"type": {
"type": "string"
}
},
"description": "Entity (e.g. agent) that produced this response.",
"additionalProperties": false
},
"memory": {
"anyOf": [
{},
{
"type": "null"
}
],
"description": "orq.ai memory store reference attached to this response."
},
"object": {
"enum": [
"response"
],
"type": "string",
"default": "response",
"description": "The object type, which was always `response`."
},
"output": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"id",
"status",
"role",
"content"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the message."
},
"role": {
"allOf": [
{
"enum": [
"user",
"assistant",
"system",
"developer"
],
"type": "string"
},
{}
]
},
"type": {
"enum": [
"message"
],
"type": "string",
"default": "message",
"description": "The type of the message. Always set to `message`."
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string"
},
{}
]
},
"content": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"video_url"
],
"properties": {
"type": {
"enum": [
"input_video"
],
"type": "string",
"description": "The type of the input content. Always `input_video`."
},
"video_url": {
"type": "string",
"description": "A base64 or remote url that resolves to a video file."
}
},
"description": "A content block representing a video input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The content of the message"
}
},
"description": "A message to or from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"call_id",
"name",
"arguments",
"status"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the function call item."
},
"name": {
"type": "string",
"description": "The name of the function that was called."
},
"type": {
"enum": [
"function_call"
],
"type": "string",
"default": "function_call",
"description": "The type of the item. Always `function_call`."
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string"
},
{}
]
},
"call_id": {
"type": "string",
"description": "The unique ID of the function tool call that was generated."
},
"arguments": {
"type": "string",
"description": "The arguments JSON string that was generated."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
}
},
"description": "A function tool call that was generated by the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"call_id",
"output",
"status"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the function tool call output. Populated when this item is returned via API."
},
"type": {
"enum": [
"function_call_output"
],
"type": "string",
"default": "function_call_output",
"description": "The type of the function tool call output. Always `function_call_output`."
},
"output": {
"anyOf": [
{
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
}
},
{
"type": "string"
}
]
},
"status": {
"allOf": [
{
"enum": [
"in_progress",
"completed",
"incomplete"
],
"type": "string",
"description": "Similar to `FunctionCallStatus`. All three options are allowed here for compatibility, but because in practice these items will be provided by developers, only `completed` should be used."
},
{}
]
},
"call_id": {
"type": "string",
"description": "The unique ID of the function tool call generated by the model."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
}
},
"description": "A function tool call output that was returned by the tool.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"id",
"summary"
],
"properties": {
"id": {
"type": "string",
"description": "The unique ID of the reasoning item."
},
"type": {
"enum": [
"reasoning"
],
"type": "string",
"default": "reasoning",
"description": "The type of the item. Always `reasoning`."
},
"content": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The reasoning content that was generated."
},
"summary": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The text input to the model."
},
"type": {
"enum": [
"input_text"
],
"type": "string",
"default": "input_text",
"description": "The type of the input item. Always `input_text`."
}
},
"description": "A text input to the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text",
"annotations",
"logprobs"
],
"properties": {
"text": {
"type": "string",
"description": "The text output from the model."
},
"type": {
"enum": [
"output_text"
],
"type": "string",
"default": "output_text",
"description": "The type of the output text. Always `output_text`."
},
"logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes",
"top_logprobs"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
},
"top_logprobs": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"logprob",
"bytes"
],
"properties": {
"bytes": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
}
},
"token": {
"type": "string"
},
"logprob": {
"type": "number"
}
},
"description": "The top log probability of a token.",
"additionalProperties": false
}
}
},
"description": "The log probability of a token.",
"additionalProperties": false
}
},
"annotations": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"url",
"start_index",
"end_index",
"title"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the web resource."
},
"type": {
"enum": [
"url_citation"
],
"type": "string",
"default": "url_citation",
"description": "The type of the URL citation. Always `url_citation`."
},
"title": {
"type": "string",
"description": "The title of the web resource."
},
"end_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the last character of the URL citation in the message."
},
"start_index": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The index of the first character of the URL citation in the message."
}
},
"description": "An annotation that applies to a span of output text.",
"additionalProperties": false
},
"description": "The annotations of the text output."
}
},
"description": "A text output from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string",
"default": "text"
}
},
"description": "A text content.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "A summary of the reasoning output from the model so far."
},
"type": {
"enum": [
"summary_text"
],
"type": "string",
"default": "summary_text",
"description": "The type of the object. Always `summary_text`."
}
},
"description": "A summary text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The reasoning text from the model."
},
"type": {
"enum": [
"reasoning_text"
],
"type": "string",
"default": "reasoning_text",
"description": "The type of the reasoning text. Always `reasoning_text`."
}
},
"description": "Reasoning text from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"refusal"
],
"properties": {
"type": {
"enum": [
"refusal"
],
"type": "string",
"default": "refusal",
"description": "The type of the refusal. Always `refusal`."
},
"refusal": {
"type": "string",
"description": "The refusal explanation from the model."
}
},
"description": "A refusal from the model.",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"image_url",
"detail"
],
"properties": {
"type": {
"enum": [
"input_image"
],
"type": "string",
"default": "input_image",
"description": "The type of the input item. Always `input_image`."
},
"detail": {
"allOf": [
{
"enum": [
"low",
"high",
"auto"
],
"type": "string"
},
{}
]
},
"image_url": {
"type": [
"string",
"null"
]
}
},
"description": "An image input to the model. Learn about [image inputs](/ai-gateway/features/multimodal#image-input).",
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"input_file"
],
"type": "string",
"default": "input_file",
"description": "The type of the input item. Always `input_file`."
},
"file_url": {
"type": "string",
"description": "The URL of the file to be sent to the model."
},
"filename": {
"type": "string",
"description": "The name of the file to be sent to the model."
}
},
"description": "A file input to the model.",
"additionalProperties": false
}
],
"description": "A content part that makes up an input or output item."
},
"description": "The reasoning summary content that was generated."
},
"signature": {
"type": "string",
"description": "The signature of the reasoning content that was generated."
},
"created_by": {
"type": "string",
"description": "The identifier of the actor that created the item."
},
"encrypted_content": {
"type": "string",
"description": "The encrypted reasoning content that was generated."
}
},
"description": "A reasoning item that was generated by the model.",
"additionalProperties": false
},
{
"allOf": [
{
"type": "object",
"required": [
"id",
"type",
"status",
"result"
],
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"result": {},
"status": {
"type": "string"
}
},
"additionalProperties": false
},
{}
]
}
],
"description": "An item representing a message, tool call, tool output, reasoning, or other response element."
},
"description": "The output items that were generated by the model."
},
"status": {
"type": "string",
"description": "The status that was set for the response."
},
"metadata": {
"description": "Developer-defined metadata that was associated with the response."
},
"reasoning": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"effort",
"summary"
],
"properties": {
"effort": {
"anyOf": [
{
"enum": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
],
"type": "string"
},
{
"type": "null"
}
]
},
"summary": {
"anyOf": [
{
"allOf": [
{
"enum": [
"concise",
"detailed",
"auto"
],
"type": "string"
},
{}
]
},
{
"type": "null"
}
]
}
},
"description": "Reasoning configuration and metadata that were used for the response.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"telemetry": {
"type": "object",
"required": [
"trace_id",
"span_id"
],
"properties": {
"span_id": {
"type": "string"
},
"trace_id": {
"type": "string"
}
},
"description": "OpenTelemetry identifiers for this response.",
"additionalProperties": false
},
"variables": {
"type": "object",
"description": "Template variables that were applied when rendering this response.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"background": {
"type": "boolean",
"description": "Whether this request was run in the background."
},
"created_at": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The Unix timestamp (in seconds) for when the response was created."
},
"project_id": {
"type": [
"string",
"null"
],
"description": "Project ID associated with the entity that produced this response."
},
"truncation": {
"allOf": [
{
"enum": [
"auto",
"disabled"
],
"type": "string"
},
{}
]
},
"output_text": {
"type": "string",
"description": "Convenience field aggregating text from output items. Added by the OpenAI SDK on parse."
},
"temperature": {
"type": "number",
"description": "The sampling temperature that was used for this response."
},
"tool_choice": {
"anyOf": [
{
"type": "object",
"required": [
"type"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function"
}
},
"additionalProperties": false
},
{
"enum": [
"none",
"auto",
"required"
],
"type": "string"
},
{
"type": "object",
"required": [
"type",
"tools",
"mode"
],
"properties": {
"mode": {
"enum": [
"none",
"auto",
"required"
],
"type": "string"
},
"type": {
"enum": [
"allowed_tools"
],
"type": "string",
"default": "allowed_tools"
},
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"type"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"enum": [
"function"
],
"type": "string",
"default": "function"
}
},
"additionalProperties": false
}
}
},
"additionalProperties": false
}
]
},
"completed_at": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"conversation": {
"anyOf": [
{},
{
"type": "null"
}
],
"description": "orq.ai conversation context attached to this response."
},
"instructions": {
"type": [
"string",
"null"
]
},
"service_tier": {
"type": "string",
"description": "The service tier that was used for this response."
},
"top_logprobs": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The number of most likely tokens that were returned at each position, along with their log probabilities."
},
"max_tool_calls": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"presence_penalty": {
"type": "number",
"description": "The presence penalty that was used to penalize new tokens based on whether they appear in the text so far."
},
"prompt_cache_key": {
"type": [
"string",
"null"
]
},
"frequency_penalty": {
"type": "number",
"description": "The frequency penalty that was used to penalize new tokens based on their frequency in the text so far."
},
"max_output_tokens": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
]
},
"safety_identifier": {
"type": [
"string",
"null"
]
},
"incomplete_details": {
"anyOf": [
{
"allOf": [
{
"type": "object",
"required": [
"reason"
],
"properties": {
"reason": {
"type": "string",
"description": "The reason the response could not be completed."
}
},
"description": "Details about why the response was incomplete.",
"additionalProperties": false
},
{}
]
},
{
"type": "null"
}
]
},
"parallel_tool_calls": {
"type": "boolean",
"description": "Whether the model was allowed to call multiple tools in parallel."
},
"previous_response_id": {
"type": [
"string",
"null"
]
},
"prompt_cache_retention": {
"type": [
"string",
"null"
]
}
},
"description": "The complete response object that was returned by the Responses API.",
"additionalProperties": {}
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description70/100
Delete any entity in the workspace by type and ID. Supported types: agent, dataset, deployment, prompt, experiment, evaluator, knowledge, memory_store, prompt_snippet, sheet, tool.
Explain mutations, irreversible effects, or prerequisites that matter before calling this tool.
Inputs63/100
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
type
Entity type to delete. Use "prompt" for prompt library entries, "experiment" for experiments.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
id
The ID of the entity to delete
Clarify units, where to obtain this value, or conventions not already expressed in the schema.
Annotations0/100
Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.
orq-mcp setup, tools, quality score, publishing readiness, and alternatives.
How do I add orq-mcp to Claude, ChatGPT, or Cursor?
Add orq-mcp to Claude, ChatGPT, or Cursor by connecting its remote MCP URL in each client's MCP settings. In Claude, add a custom connector. In ChatGPT, add an MCP app. In Cursor, add an MCP server under Settings. The MCP URL is https://my.orq.ai/v2/mcp.
Is orq-mcp MCP ready for ChatGPT and Claude?
As of October 15, 2026, orq-mcp scores 88/100 on Manufact's MCP publishing checklist. The scan does not yet meet ChatGPT publishing checks and does not yet meet Claude publishing checks. Passing these checks does not guarantee marketplace approval.
How clear is orq-mcp's MCP tool documentation?
As of October 15, 2026, orq-mcp scores 67/100 in Manufact's review of tool titles, descriptions, input and output schemas, and behavior annotations. The review covers 47 of 47 discovered tools. The quality score measures documentation clarity; runtime behavior and marketplace readiness require separate checks.
What are the best alternatives to orq-mcp?
As of October 15, 2026, alternatives to orq-mcp in developer-tools on the Manufact MCP catalog include Held at the Gate, Speko, turva.dev, AgentMail, and Celesto Cloud Computers.
How can orq-mcp improve its MCP documentation?
update_datapoint is the lowest-scoring reviewed tool at 48/100. Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior. Open its review for feedback and a copyable fix prompt, then rerun the documentation review after updating your tool metadata.
Not your MCP?
Review any public or OAuth MCP server for protocol compatibility, tool documentation, and ChatGPT and Claude publishing readiness. No account required.