Tool Design & MCP Integration
Domain 2 covers how Claude agents reach outside their context to act on the world through **tools** and the **Model Context Protocol (MCP)**. At 18% of the CCAR-F blueprint, it tests whether you can design tool schemas Claude selects correctly, return errors an agent can recover from, distribute the right tools to the right agent, wire up MCP servers securely, and choose between custom tools and Claude's built-in capabilities. The recurring theme is that tools are a *language interface* first and a code interface second. A tool succeeds or fails on how clearly it describes itself, how honestly it reports failure, and how narrowly it is scoped. Get those right and Claude routes work accurately; get them wrong and no amount of downstream infrastructure fully compensates.
5 lessons in this domain
- 2.1
Tool Schema Design
Tool descriptions are the primary signal Claude uses to pick a tool. Learn to write schemas that route requests correctly instead of misfiring.
6 min read - 2.2
Structured Error Responses
How a tool reports failure decides whether an agent recovers intelligently or fails blindly. Learn the error categories and the empty-result trap.
6 min read - 2.3
Tool Distribution Choice
Give each agent 4-5 role-scoped tools, use tool_choice to control invocation, and add scoped cross-role tools to cut coordinator latency.
6 min read - 2.4
MCP Server Integration
MCP connects Claude to external systems. Learn config scoping, secret handling, resources vs tools, and when to build a custom server versus reusing one.
7 min read - 2.5
Built-in Tools
Claude's built-in tools each have a precise job. Learn Grep vs Glob, Edit-first modification, and incremental discovery to avoid wasting context.
5 min read