Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Tool Auditor Audit the description for my 'search' tool"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Audit any MCP tool description for LLM reliability. Detect smells, scores quality 0-100, and rewrite for better agent accuracy.
Zero external APIs. Pure computation. Built for developers who care about agent reliability.
Research in 2026 shows that 97% of MCP tool descriptions contain at least one "smell" (vague purpose, missing usage guidelines, opaque parameters). When descriptions are weak, AI agents pick the wrong tool or waste steps.
This MCP server lets you (or your agent) audit and fix those descriptions before you publish.
Related MCP server: MCP Tool Security Inspector
# Install & run with any MCP client
npx -y mcpize connect @princeruhulofficial/tool-auditor --client claudeOr add to your Claude / Cursor / other client config:
{
"mcpServers": {
"tool-auditor": {
"command": "npx",
"args": ["-y", "mcp-tool-auditor"]
}
}
}Tool | What it does |
| Score one tool description (0-100), list smells, give fix suggestions |
| Generate a high-quality rewritten description ready to paste |
| Audit a full list of tools — detect overcrowding + rank quality |
| Return the current best-practice checklist for MCP tool descriptions |
If you are building AI products or selling MCP servers:
Agents that pick the wrong tool = wasted tokens + angry users
High-quality tool descriptions = higher task success rate
This server is free to run (no API bills) and can be called by your own agents during development
Free: 100 audits / day
Pro $9/mo: 2 000 audits / day
npm install
npm run build
npm run test:smokeMIT © Prince Ruhul / Prevalid
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.
Inputs: name (required), description (required), inputSchema.
Audit an entire list of tools at once. Detects overcrowding (too many tools hurt accuracy), ranks each tool by quality score, and flags the worst offenders. Research shows accuracy drops below 90% when weaker models see more than 10-15 tools.
Inputs: tools (required).
Return the current checklist of MCP tool-description best practices derived from research (2026 papers + real-world agent testing). Use this as a reference when writing new tools.
Inputs: no named parameters.
Rewrite a weak tool description into a high-quality, LLM-optimized version that follows current best practices (clear purpose, usage guidelines, parameter hints, limitations). Returns the improved description ready to paste into your MCP server.
Inputs: name (required), description (required), context, inputSchema.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
Audit_tool and audit_tool_list overlap in purpose (auditing descriptions) but are clearly separated by scope (single vs. list). Rewrite and best practices are distinct. The descriptions make the boundaries clear, so confusion is unlikely.
All tool names follow a consistent verb_noun pattern in snake_case (audit_tool, rewrite_tool_description, audit_tool_list, get_best_practices). No mixed casing or stylistic deviations.
Four tools is well-scoped for the server's purpose. Each tool addresses a distinct step in the auditing workflow: reference, single audit, batch audit, and rewrite.
The core workflow is covered: get best practices, audit individual or list, and rewrite weak descriptions. A minor gap is lack of a validation/apply tool after rewriting, but the existing set supports the main use case effectively.
Grade MCP tool definitions for agent-readiness: score, A-F grade, fixes, est. token cost.
Statically audits MCP tool surfaces for token cost, schema quality, and design issues.
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
Score MCP tool definitions 0-100. Checks names, schemas, annotations, and uniqueness.