# toolsmell

> toolsmell — munzzyy-toolsmell. Use this tool when you need to identify and fix issues in MCP server tool descriptions and JSON schemas that can lead to suboptimal agent performance. It lints server configurations to detect "smells" that negatively impact tool usage, providing outputs that highlight areas for improvement. Ideal for use in git-based workflows to optimize tool descriptions and schemas for better agent interaction.

Canonical page: https://skillsregistry.net/skills/munzzyy-toolsmell  
JSON: https://api.skillsregistry.net/v1/skills/munzzyy-toolsmell

## Description

Lint an MCP server's tool descriptions and JSON schemas for smells that make agents use the tools worse.

## Trust

- **Trust score (0–1):** 0.90
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/munzzyy/toolsmell)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "munzzyy-toolsmell"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/munzzyy-toolsmell` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/munzzyy-toolsmell/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt