MoneyTools Inference Fidelity Audit

fidelity_bill_check

Read-onlyIdempotent

Recount visible tokens vs seller usage/charge. Free 5/day then 0.003 USDC.

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": {
      "response": "<response>"
    },
    "name": "fidelity_bill_check"
  }
}

Input Schema

Name	Required	Description
`model`	No	Claimed model id (informational)
`request`	No	Original request (messages) for input size estimate
`response`	Yes	Seller response object with content and optional usage {prompt_tokens,completion_tokens}
`chargedUsd`	No	Amount charged in USDC (optional)
`priceTable`	No	Optional {inputPerMTok, outputPerMTok} USD per million tokens
`chargedAtomic`	No	Amount charged in USDC atomic units (1e6 = 1 USDC)

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

B3.1/5.0

Behavior3/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, non-open-world), and the description usefully adds the commercial constraint: 5 free calls per day, then 0.003 USDC per call. It says nothing about what the tool returns (pass/fail verdict, discrepancy figures) or how it behaves when the response lacks a usage block, which matters since there is no output schema.

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?

Two short sentences with the purpose front-loaded and the cost/quota as supporting detail; nothing is padded. It is terse to the point of under-specification, but no sentence is wasted.

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

Completeness2/5

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

With six parameters including a nested request and response, plus no output schema, the definition should describe the return value and the minimum viable input. It gives none of that, leaving an agent unsure what a successful result looks like or which optional billing fields to supply.

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 coverage is 100%, so every parameter already has a description; the description text itself contributes no parameter meaning. It does not clarify precedence between chargedUsd and chargedAtomic, or what happens if neither is supplied, which are the real ambiguities in this schema.

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?

"Recount visible tokens vs seller usage/charge" gives a concrete verb (recount/compare) and two concrete resources (visible tokens, claimed usage/charge), so an agent knows this is a billing/token reconciliation tool. It stops short of naming how it differs from sibling checks such as fidelity_quick_check or fidelity_audit.

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

Usage Guidelines2/5

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

There is no statement of when to use this versus the sibling check/audit/report tools, and no prerequisites or exclusions. The pricing sentence describes cost, not selection guidance.

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?