MCP Agent Readiness
Find out whether an agent can actually choose correctly within a toolset. Reports pairs of tools whose words overlap enough to be confusable, descriptions too short or too empty to distinguish, undescribed arguments an agent must guess at, tools with so many arguments they are filled wrong, state-changing tools with no annotation hints, and the total size of the manifest, which occupies the model context on every turn.
Inferenceofflineeip155:8453Exactvia cdp
McpAgent toolingTool selectionContext costDeveloper tooling
Settlements · 30d
224↑ 25%
No per-endpoint history for this service yet, so this is payments indexed to its PROVIDER's wallet over 30 days.
$25.38
Verified settled volume
261 settlements proven x402 by their on-chain EIP-3009 marker.
$0.180
Listed price
As published in the catalog. Always read the live 402 before paying.
1
Calls · 30d
Upstream's own call count for this endpoint, not ours.
1
Unique payers · 30d
Last called 2026-10-04 07:57Z
—
Upstream on-chain volume
Reported by the source catalog.
Paid to
0x25e8245f07d5e4873987293dad666afbe56a9608The wallet the 402 directs payment to. Its whole payment record — every payer, every chain — is on the merchant page.
Asset 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913
Provider
The payTo wallet does not resolve to a registered ERC-8004 agent. That is not a verdict on the service — most of the catalog is unregistered.
Accepts
The payment requirements as published to the catalog. Read the live 402 before paying — a price here is a claim, not a quote.
0.18USDC≈ $0.18 USD
on Base · exact scheme
Pay 0.18 USDC on Base to 0x25e8…a9608. The signed payment is good for 1 minute.
- Paid to
- 0x25e8…a9608
- USD Coin contract
- 0x8335…02913
- Payment window
- 1 minute
- As published
- 180000 smallest units
The catalog’s raw entry
[
{
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"extra": {
"name": "USD Coin",
"version": "2"
},
"payTo": "0x25e8245f07d5e4873987293dad666afbe56a9608",
"amount": "180000",
"scheme": "exact",
"network": "eip155:8453",
"maxTimeoutSeconds": 60
}
]Extensions
{
"bazaar": {
"info": {
"input": {
"body": {
"toolset": {
"tools": [
{
"name": "fetch_user",
"description": "Fetch a user record by id.",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "User id."
}
}
}
},
{
"name": "get_user",
"description": "Fetch a user record by id.",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {}
}
}
},
{
"name": "do_thing",
"description": "Does.",
"inputSchema": {
"type": "object",
"properties": {}
}
},
{
"name": "sync_everything",
"description": "Send every pending change upstream and overwrite remote state.",
"inputSchema": {
"type": "object",
"properties": {
"field_0": {
"type": "string",
"description": "Field 0."
},
"field_1": {
"type": "string",
"description": "Field 1."
},
"field_2": {
"type": "string",
"description": "Field 2."
},
"field_3": {
"type": "string",
"description": "Field 3."
},
"field_4": {
"type": "string",
"description": "Field 4."
},
"field_5": {
"type": "string",
"description": "Field 5."
},
"field_6": {
"type": "string",
"description": "Field 6."
},
"field_7": {
"type": "string",
"description": "Field 7."
},
"field_8": {
"type": "string",
"description": "Field 8."
},
"field_9": {
"type": "string",
"description": "Field 9."
},
"field_10": {
"type": "string",
"description": "Field 10."
},
"field_11": {
"type": "string",
"description": "Field 11."
},
"field_12": {
"type": "string",
"description": "Field 12."
},
"field_13": {
"type": "string",
"description": "Field 13."
}
}
}
}
]
},
"max_manifest_characters": 2000
},
"type": "http",
"method": "POST",
"bodyType": "json"
},
"output": {
"type": "json",
"example": {
"limits": {
"maxCalls": 1000,
"maxTools": 400,
"maxServers": 20,
"maxFindings": 500,
"confusableOverlap": 0.6
},
"passed": false,
"complete": true,
"findings": [
{
"code": "ARGUMENTS_UNDESCRIBED",
"tool": "get_user",
"detail": "get_user: id have no description, which is what an agent reads to fill them.",
"arguments": [
"id"
]
},
{
"code": "DESCRIPTION_TOO_SHORT",
"tool": "do_thing",
"detail": "do_thing has a 5-character description, below the 20 needed to distinguish it."
},
{
"code": "DESCRIPTION_UNINFORMATIVE",
"tool": "do_thing",
"detail": "do_thing: the description carries almost no information beyond the name."
}
],
"request_id": "example-request",
"service_id": "mcp_agent_readiness_audit",
"agent_ready": false,
"assumptions": [
"An agent selects a tool from its name and description and fills it from argument descriptions, so those are functional surfaces rather than documentation.",
"Every tool definition occupies the model context on every turn, so manifest size is a running cost.",
"Confusability is measured by overlap of significant words. It is deterministic and crude on purpose: it prompts a rename rather than claiming two tools do the same thing."
],
"limitations": [
"A structural readiness audit, not an evaluation. It does not run a model, measure real selection accuracy, or call any tool.",
"agent_ready is true only when the whole toolset was read and nothing an agent needs to choose correctly was missing."
],
"observed_at": "2026-10-02T00:00:00.000Z",
"not_examined": [],
"finding_count": 6,
"read_tool_count": 4,
"service_version": "1.0.0",
"confusable_pairs": [
{
"tools": [
"fetch_user",
"get_user"
],
"overlap": 0.75
}
],
"findings_by_code": {
"TOO_MANY_ARGUMENTS": 1,
"ARGUMENTS_UNDESCRIBED": 1,
"DESCRIPTION_TOO_SHORT": 1,
"MUTATION_HINTS_ABSENT": 1,
"DESCRIPTION_UNINFORMATIVE": 1,
"TOOLS_POTENTIALLY_CONFUSABLE": 1
},
"manifest_characters": 1139,
"confusable_pair_count": 1,
"manifest_character_budget": 2000,
"tools_with_many_arguments": [
"sync_everything"
]
}
}
},
"schema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"input"
],
"properties": {
"input": {
"type": "object",
"required": [
"type",
"method",
"bodyType",
"body"
],
"properties": {
"body": {
"type": "object",
"required": [
"toolset"
],
"properties": {
"toolset": {},
"max_manifest_characters": {
"type": "integer",
"minimum": 500
},
"min_description_characters": {
"type": "integer",
"minimum": 0
}
},
"additionalProperties": false
},
"type": {
"type": "string",
"const": "http"
},
"method": {
"enum": [
"POST"
],
"type": "string"
},
"bodyType": {
"enum": [
"json",
"form-data",
"text"
],
"type": "string"
}
},
"additionalProperties": false
},
"output": {
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"type": "string"
},
"example": {
"type": "object"
}
}
}
}
}
}
}Provenance
- Seen in the source catalog
- 2026-10-04 07:58Z
- Last indexed by Roundhouse
- 2026-10-05 00:20Z
- Last enriched (probe, favicon, geo)
- 2026-10-04 11:16Z
- x402 version
- 2
- Max timeout
- 60s
- Liveness probe
- HTTP 0
Hand this page to an agent
Copy the prompt and paste it into Claude, an MCP client or your own agent — it will vet this service and call it over the free read API. No key, no account.
GET api.roundhouseai.io/v0/endpoints
No per-endpoint history for this service yet, so this is payments indexed to its PROVIDER's wallet over 30 days. Verified volume counts only settlements with an on-chain EIP-3009 marker.
Show the promptHide the prompt
Using Roundhouse, look up the x402 service MCP Agent Readiness and tell me whether it is worth paying: what a call costs, whether the endpoint answered when last probed, and what its payment record actually shows. curl -s 'https://api.roundhouseai.io/v0/endpoints?q=MCP%20Agent%20Readiness' curl -s 'https://api.roundhouseai.io/v0/merchants/<the payTo wallet returned above>' Then call it: read the price from the live 402 at https://api.zfinia.com/x402/v1/mcp-agent-readiness-audit, never from a cached figure, and pay with an x402 client. The /v0 API needs an API key (`authorization: Bearer rh_live_…`) on everything except /v0/unified* and /v0/endpoints. Either pay over x402 (mint a personal key for $0.01 at GET https://api.roundhouseai.io/v0/test/x402), or ask me for an organization key, which I create at https://roundhouseai.io/dashboard/connections. If you have neither, ask before going further. If you do not have Roundhouse tools or skills installed, read https://roundhouseai.io/skill.md first — it is the whole procedure.