Title56/100
Not provided
Add a human-readable title so users do not have to interpret the tool identifier.
Description98/100
Answers a single analytical question about private-market data and returns structured tabular results (columns + rows). Read-only. Use this for analytical queries — aggregations, counts, rankings, comparisons, computed metrics, and trend analysis. For entity discovery (e.g. "find startups matching X criteria"), prefer ``cb_expert_build_search`` with ``preview_limit``. For profile details on a specific entity, prefer ``cb_expert_resolve_entity`` or ``cb_entity_get``. Each call answers exactly one question. Break multi-part questions into separate calls. Do NOT include "from Crunchbase" in the question text. Replace relative dates ("since Covid") with absolute dates ("since Dec 2019"). For detailed input guidelines and prompt patterns, call ``cb_reference('guidance/query_answer')``. Each profile entity in the results carries a ``url`` field — when presenting results to the user, render it as a markdown link ``[value](url)`` and never omit it. **Token cost:** for example, ~10,000 data tokens; scales with the data involved. Args: question: Natural language question/request to answer from Crunchbase data. Returns: Structured table results and associated metadata.
The description explains the capability, when to use it, and what to expect.
Inputs0/100
0 of 1 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
question
Not provided
Missing description. Explain what this value means and how to supply it.
Annotations100/100
All four behavior hints are declared.
{
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}Output schema88/100
The output schema explains the structured result.
View output schema
{
"type": "object",
"properties": {
"rows": {
"type": "array",
"items": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"value",
"uuid",
"entity_def_id",
"url"
],
"properties": {
"url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"readOnly": true,
"description": "Crunchbase profile page URL for linkable entity types."
},
"uuid": {
"type": "string",
"description": "Globally unique id of this entity."
},
"value": {
"type": "string",
"description": "Human-readable entity display name."
},
"permalink": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Crunchbase permalink slug when available."
},
"entity_def_id": {
"type": "string",
"description": "Crunchbase entity type identifier."
}
},
"description": "Typed entity identity cell for answer results."
},
{}
]
}
},
"description": "Row-major result data. Cells are JSON scalars or EntityCell objects with entity identity."
},
"error": {
"anyOf": [
{
"type": "object",
"required": [
"code",
"message"
],
"properties": {
"code": {
"type": "string",
"description": "Machine-readable error code."
},
"message": {
"type": "string",
"description": "Human-readable error message."
}
},
"description": "Uniform error payload shared by all MCP tool output models."
},
{
"type": "null"
}
],
"default": null,
"description": "Error payload if the tool failed."
},
"columns": {
"type": "array",
"items": {
"type": "string"
},
"description": "Result column names."
},
"row_count": {
"type": "integer",
"default": 0,
"description": "Number of rows returned."
},
"truncated": {
"type": "boolean",
"default": false,
"description": "True if results were truncated due to max row limit."
},
"request_id": {
"type": "string",
"description": "Request ID for tracking this tool invocation end-to-end."
},
"follow_up_action": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Action the caller should take after presenting results. When set to 'collect_feedback', prompt the user and then call cb_expert_submit_feedback."
},
"follow_up_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Suggested prompt to present to the user when follow_up_action is set."
},
"answered_question": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Narrowed interpretation of the user's question that the planner actually answered, when it chose to scope down. Null when the answer addresses the question as asked."
},
"resolved_references": {
"type": "array",
"items": {
"type": "object",
"required": [
"matched_literal"
],
"properties": {
"identifier": {
"anyOf": [
{
"type": "object",
"properties": {
"uuid": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Globally unique id of this entity."
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Textual representation of this entity (i.e. its name)."
},
"image_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Location to obtain an image."
},
"permalink": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Unique nice id within its entity def."
},
"entity_def_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "What type of entity this is."
}
},
"description": "Crunchbase identifier from entity resolution. Carries additionalProperties.",
"additionalProperties": true
},
{
"type": "null"
}
],
"default": null,
"description": "Crunchbase identifier object from entity resolution, if resolved."
},
"matched_literal": {
"type": "string",
"description": "Exact canonical literal used in the query."
}
},
"description": "An entity reference from the question resolved to a canonical Crunchbase record."
},
"description": "Entities referenced in the question that were resolved to canonical Crunchbase records."
}
},
"description": "Structured output for `expert_query_answer`."
}