Cursor
Grok Bot
Grok
MuseTitle89/100
Check an x402 seller before paying
The title clearly communicates the tool’s action and subject. Keep it concise.
Description99/100
Call this before any x402 payment, before retrying a request that answered HTTP 402, or whenever the user is about to buy an API call with USDC on Base or names an API they intend to pay per call. Returns a verdict (avoid, caution, ok, unknown), one sentence to act on, the seller's paid-call count and failure rate with a 95% interval, listed price, modal quote and max overcharge ratio when known, and links to the seller page and raw evidence.
The description explains the capability, when to use it, and what to expect.
Inputs95/100
Input documentation gives an agent enough context to populate the arguments.
url
x402 resource URL, or a bare seller domain such as api.example.com
Clear enough to supply this argument.
Annotations100/100
All four behavior hints are declared.
{
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}Output schema84/100
The output schema explains the structured result.
View output schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"verdict",
"verdict_text",
"host",
"seller",
"resource",
"probe",
"candidate",
"seller_url",
"evidence_url",
"methodology_url",
"generated_at"
],
"properties": {
"host": {
"type": [
"string",
"null"
]
},
"probe": {
"anyOf": [
{
"type": "object",
"properties": {},
"additionalProperties": {}
},
{
"type": "null"
}
],
"description": "Hourly unpaid probes of the seller's 402 quote; null when not probed"
},
"seller": {
"anyOf": [
{
"type": "object",
"required": [
"domain",
"calls",
"failures",
"failure_rate",
"wilson_low",
"wilson_high",
"by_type",
"low_sample",
"last_seen"
],
"properties": {
"calls": {
"type": "number"
},
"domain": {
"type": "string"
},
"by_type": {
"type": "object",
"description": "Failure counts by type (non_delivery, overcharge, duplicate, wrong_goods)",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "number"
}
},
"failures": {
"type": "number"
},
"last_seen": {
"type": "string"
},
"low_sample": {
"type": "boolean"
},
"wilson_low": {
"type": "number",
"description": "95% interval lower bound on the failure rate"
},
"wilson_high": {
"type": "number",
"description": "95% interval upper bound on the failure rate"
},
"failure_rate": {
"type": "number"
}
},
"additionalProperties": false
},
{
"type": "null"
}
],
"description": "Measured paid calls to this seller; null when the study never paid it"
},
"verdict": {
"enum": [
"avoid",
"caution",
"ok",
"unknown"
],
"type": "string"
},
"resource": {
"anyOf": [
{
"type": "object",
"required": [
"url",
"method",
"listed_price_usdc",
"modal_quote_usdc",
"max_quote_usdc",
"max_overcharge_ratio",
"calls",
"failure_rate"
],
"properties": {
"url": {
"type": "string"
},
"calls": {
"type": "number"
},
"method": {
"type": "string"
},
"failure_rate": {
"type": "number"
},
"max_quote_usdc": {
"type": [
"string",
"null"
]
},
"modal_quote_usdc": {
"type": [
"string",
"null"
]
},
"listed_price_usdc": {
"type": [
"string",
"null"
]
},
"max_overcharge_ratio": {
"type": [
"number",
"null"
]
}
},
"additionalProperties": false
},
{
"type": "null"
}
],
"description": "Measured paid calls to this exact URL; null when not measured"
},
"candidate": {
"anyOf": [
{
"type": "object",
"properties": {},
"additionalProperties": {}
},
{
"type": "null"
}
],
"description": "Queue state for a seller not yet measured; null otherwise"
},
"seller_url": {
"type": [
"string",
"null"
]
},
"evidence_url": {
"type": [
"string",
"null"
]
},
"generated_at": {
"type": "string",
"description": "When the index was generated"
},
"verdict_text": {
"type": "string",
"description": "One sentence to act on, with the evidence link"
},
"methodology_url": {
"type": "string"
}
},
"additionalProperties": false
}