Your MCP server's tool descriptions are the product: a 40-line Node script to dump and review them

A developer published a dependency-free 40-line Node script that spawns any stdio MCP server, performs the initialize handshake, calls tools/list, and prints each tool's name, description and inputSchema parameters so authors can see what an agent actually reads. The post argues that vague tool descriptions cause models to pick the wrong tool or skip the right one, citing Glama's TDQS spec for scoring tool-definition quality, and offers a pay-what-you-want CLI, MCP Tool Docs Generator, that writes TOOLS.md, per-tool Markdown pages and tools.json.

Agents pick MCP tools by reading name , description and inputSchema from tools/list . If those are vague, the model picks the wrong tool, or skips the right one. Glama recently published an open spec for scoring this TDQS, https://tdqs.dev https://tdqs.dev , and the main complaint it addresses is inconsistent tool definitions. Before you submit a server to a directory, read what an agent actually sees. Here is a dependency-free Node script that spawns any stdio MCP server, runs the handshake, and prints every tool. js // dump-tools.mjs - usage: node dump-tools.mjs <command args... import { spawn } from "node:child process"; const cmd, ...args = process.argv.slice 2 ; const p = spawn cmd, args, { stdio: "pipe", "pipe", "inherit" } ; let buf = ""; const pending = new Map ; let id = 0; p.stdout.on "data", d = { buf += d; let i; while i = buf.indexOf "\n" = 0 { const line = buf.slice 0, i .trim ; buf = buf.slice i + 1 ; if line continue; try { const m = JSON.parse line ; if m.id = null && pending.has m.id pending.get m.id m ; } catch {} } } ; const send = method, params = new Promise res = { const myId = ++id; pending.set myId, res ; p.stdin.write JSON.stringify { jsonrpc: "2.0", id: myId, method, params } + "\n" ; } ; await send "initialize", { protocolVersion: "2024-11-05", capabilities: {}, clientInfo: { name: "dump-tools", version: "0.1.0" }, } ; p.stdin.write JSON.stringify { jsonrpc: "2.0", method: "notifications/initialized" } + "\n" ; const { result } = await send "tools/list", {} ; for const t of result.tools { const props = Object.keys t.inputSchema?.properties ?? {} ; console.log ${t.name}\n${t.description ?? " NO DESCRIPTION "}\nparams: ${props.join ", " || "none"}\n ; } p.kill ; NO DESCRIPTION line is a tool the model has to guess about. get user: Gets a user tells the model nothing. Say what it returns and when to use it instead of a sibling tool. inputSchema for its own description , units and an example. A terminal dump is fine for you, but reviewers and users want a readable page. I packaged the same idea as a small zero-dependency CLI called MCP Tool Docs Generator. It connects to a stdio MCP server, calls initialize and tools/list , and writes a TOOLS.md , one Markdown page per tool, and a tools.json . It is pay-what-you-want with a $1 minimum: https://renevibe76.gumroad.com/l/bmzwpm https://renevibe76.gumroad.com/l/bmzwpm The script above is free to copy and enough to audit your own server. The packaged version is for when you want the files generated for your README.