MCP Tool Auditor

audit_tool

Audit MCP tool descriptions to score quality 0-100, detect vague purpose or missing guidelines, and get fix suggestions before publishing.

Instructions

Audit a single MCP tool description for LLM reliability. Returns a 0-100 quality score, list of detected smells (vague purpose, missing usage guidelines, opaque params, etc.), and concrete fix suggestions. Use this before publishing any MCP server.

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": {
      "name": "<name>",
      "description": "<description>"
    },
    "name": "audit_tool"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	The exact name of the tool (e.g. 'search_web')
`description`	Yes	The current human-readable description of the tool
`inputSchema`	No	The JSON Schema of the tool's input parameters (optional but recommended for deeper analysis)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Aug 10, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations, the description carries the full burden. It explicitly discloses the return value (0-100 quality score, list of detected smells, concrete fix suggestions), giving a transparent picture of behavior. It does not mention side effects or permissions, but as a read-only audit tool, the output description is sufficient for most contexts.

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

Conciseness5/5

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

The description is exactly two sentences: the first states the purpose, the second states the output and usage context. It is front-loaded, concise, and every sentence adds value with no superfluous content.

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?

For a tool with 3 parameters and no output schema, the description explains the output format (score, smells, fixes) and the context (before publishing). It lacks explicit error handling or limitations, but given the simplicity of an audit tool, this is adequate. A slightly higher score would require explicitly stating it is read-only or defining 'LLM reliability.'

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%, meaning all parameters are already documented in the schema. The description does not add parameter-specific details beyond the overall purpose, which implies the 'description' is the main artifact being audited. This meets the baseline for high schema coverage.

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

Purpose5/5

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

The description clearly states the tool audits a single MCP tool description for LLM reliability, using the specific verb 'Audit' and specifying the resource ('single MCP tool description'). This distinguishes it from sibling tools like audit_tool_list (likely batch auditing) and rewrite_tool_description (rewriting descriptions).

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?

The description provides a clear usage scenario: 'Use this before publishing any MCP server.' It implies the tool is for pre-publication validation. While it does not explicitly name alternatives or list when-not-to-use conditions, the qualifier 'single' differentiates it from batch tools like audit_tool_list, offering adequate guidance.

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

Deploy Server