Put the MCP tool discovery and invocation steps in the correct order

Attempt it

1Server executes the tool and returns a `content` array (with optional `isError: true`)
2Host injects tool descriptions into the LLM's context
3Host sends `tools/call` with `name` and `arguments` to the server
4LLM decides to call a tool and emits a structured function-call request
5Server returns an array of tool objects, each with `name`, `description`, and `inputSchema`
6Host sends `tools/list` to the server to discover available tools

Quick reference

TL;DR

MCP tool use is discovery-before-call: the host lists tools, injects their schemas into the model, the model picks one, then the host invokes it and returns the result.

Memory aid

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

Easy to grasp

Imagine walking into a workshop you've never seen. First you read the labels on every machine to learn what each does and which buttons it needs. That is the host asking the server for its tool list. Then you decide which machine fits your task, set its dials correctly, and press start. That is the model picking a tool and the host running it. The machine does its work and hands you the finished part, which is the server returning a result. You never press start before reading the labels, because you would not know what the machine expects. MCP enforces the same order: discover what exists and how to call it, then call it.

Key concepts

LLM tool use Capability discovery JSON-RPC transport

Quick scan · 2–4 min

Everything important, quickly.

4 min: handshake then tools/list discovery, schema injection into the model, model selection, tools/call dispatch, content array result, and why the order cannot invert.

Side-by-side

Step	Message	Direction
Discover tools	tools/list	Host to server
Return catalog	Array with name, description, inputSchema	Server to host
Expose to model	Tool definitions injected into context	Host to model
Model selects	Structured function-call request	Model to host
Invoke tool	tools/call with name and arguments	Host to server
Return result	content array, optional isError true	Server to host

Real-world examples

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

Claude Code calls tools/list on each configured server at session start, then injects the discovered tools as Anthropic tool definitions.
Cursor and Zed run the same discover-then-call loop over JSON-RPC, so any MCP server written once works across all three hosts.
The mcp-inspector tool lets you watch the tools/list response and the tools/call round-trip live while building a server.

Interviewer follow-ups

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

QHow does the host handle two servers that both advertise a tool named search?

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

QWhat changes if the tool list can change mid-session rather than only at startup?

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

QWhere does user approval fit into this order, and why does its placement matter?

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.