Complete the key fields in a tools/list tool object and a tools/call request

Attempt it

A tool returned by `tools/list` has three required fields: `` (the tool identifier), `` (human-readable explanation the LLM uses when deciding to call), and `` (a JSON Schema that defines the expected arguments). A `tools/call` request sends `` (to identify which tool) and `` (the argument values).

Quick reference

TL;DR

A tools/list tool carries name, description, and inputSchema; a tools/call request sends name plus arguments and gets back a content array with optional isError.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Think of a restaurant menu. Each dish has a name, a short description so you know what it is, and a list of choices you can customize, like spice level or sides. That menu is what tools/list returns: every tool's name, its description, and its inputSchema describing valid options. When you order, you don't recite the whole menu. You just say the dish name plus your choices, which is exactly what tools/call sends: name and arguments. The kitchen then hands back your plate, the content array, and if something went wrong it tells you, the isError flag. The menu lets you browse; the order form lets you act.

Key concepts

MCP tools primitive inputSchema (JSON Schema)JSON-RPC 2.0

Quick scan · 2–4 min

Everything important, quickly.

4 min: discovery vs invocation split, the three list fields, the two call fields, the content array result, and the isError versus JSON-RPC error contract.

Side-by-side

Aspect	tools/list	tools/call
Direction	Host asks, server answers	Host invokes, server runs
Key fields	name, description, inputSchema	name, arguments
Returns	Array of tool descriptors	content array (+ optional isError)
When called	Once at discovery time	Every time the model picks a tool
Failure signal	JSON-RPC error if not supported	isError true inside the result

Real-world examples

Real products, models, and research that use this idea.

Claude Code calls `tools/list` on every configured MCP server at session start, then maps each descriptor into an Anthropic tool definition.
The official filesystem MCP server publishes tools like `read_file` with an `inputSchema` requiring a `path` string argument.
The mcp-inspector debugging tool shows raw `tools/list` and `tools/call` JSON-RPC traffic, including the `content` array and `isError` flag.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QWhy does MCP put tool execution failures in the result via isError instead of the JSON-RPC error channel?

Sign in or go Pro to see the approach for this follow-up.

QHow does a host map an MCP tool descriptor onto a specific model's function-calling format?

Sign in or go Pro to see the approach for this follow-up.

QWhat problems arise when two connected servers expose tools with the same name?

Sign in or go Pro to see the approach for this follow-up.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.