# Toolmetry

> Measure how well AI agents actually use your MCP server's tools — then rewrite the tool descriptions and prove the improvement with before/after data.

## Facts
- Page: https://tashan.sh/capability/pkg-mcp-toolmetry
- tashan id: pkg:mcp-toolmetry
- Source: https://github.com/sujugithub/toolmetry
- npm: https://www.npmjs.com/package/mcp-toolmetry
- Type: npm
- Category: other
- tashan score: 42.0 / 100
- Adoption: 18.0
- Upkeep: 55.0
- Freshness: 89.0
- Evidence coverage: 100% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- npm downloads: 19/week
- Official: no

## Install

```sh
claude mcp add toolmetry -- npx -y mcp-toolmetry
```

## Security audit
- Known advisories: 0
- Install-time script: none declared
- Build provenance: not attested

Permissions are read from DECLARED dependencies only. Nothing is executed, so an empty result means "nothing declared", never "nothing possible".

---
Measured 2026-08-14 by tashan (https://tashan.sh) from public evidence. Scorer s5.