MoneyTools Inference Fidelity Audit

fidelity_quick_check

Read-only

1-probe indicative check of a seller vs Cloudflare Workers AI reference (cheaper than a full audit). Free 3/day then 0.005 USDC via x402 (MCP: params._meta["x402/payment"]). Auth header never stored.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "endpoint": "<endpoint>",
      "model": "<model>"
    },
    "name": "fidelity_quick_check"
  }
}

Input Schema

Name	Required	Description
`model`	Yes	Claimed model id. Supported: llama-3.1-8b, llama-3.2-3b, llama-3.3-70b, llama-4-scout, qwen3-30b, qwen2.5-coder-32b, gpt-oss-20b, gpt-oss-120b, gemma-4-26b, glm-4.7-flash
`endpoint`	Yes	OpenAI-compatible base URL (https://…/v1) or chat completions URL
`authHeader`	No	Optional Authorization value for the target. Used in memory only; never stored or logged.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 10, 2026

changedInput schema / properties / endpoint / description

Previous value: -"OpenAI-compatible base URL (https://…/v1) or chat completions URL, or \"workers-ai\""New value: +"OpenAI-compatible base URL (https://…/v1) or chat completions URL"

First observedNov 10, 2026

TDQS

A4.1/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/openWorld annotations, the description declares the commercial and privacy behavior an agent cannot otherwise know: a free tier of 3/day, then 0.005 USDC charged via x402 with the exact MCP payment location (params._meta["x402/payment"]), and that the auth header is never stored. Those are precisely the cost, rate-limit, and data-handling facts annotations don't carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is front-loaded in one clause, followed by the cost and payment mechanics in tightly compressed parentheticals. It is dense but every element (cheaper, free tier, price, payment channel, no auth storage) carries information; only the nested quoting makes it slightly hard to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the definition still covers cost, payment channel, privacy, and comparative scope, which is most of what an agent needs before calling. The remaining gap is that it never says what the check returns or what 'indicative' means in practice (pass/fail vs. a similarity score).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: model, endpoint, and authHeader are all documented in the schema, including the supported model list and the 'in memory only' note. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete verb and resource: a '1-probe indicative check of a seller vs Cloudflare Workers AI reference', which tells the agent exactly what is compared and at what depth. The parenthetical 'cheaper than a full audit' implicitly separates it from fidelity_audit, though it doesn't name the sibling explicitly, so it falls just short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Indicative' plus 'cheaper than a full audit' gives clear context for choosing this over the heavier audit path. There is no explicit when-not-to-use clause or named alternative, so the agent has to infer that fidelity_audit is the escalation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All MoneyTools Inference Fidelity Audit tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?