Domain 2 · 18% of the exam
Tool Design & MCP Integration
Design effective tool schemas, implement MCP servers and clients, and integrate external services into Claude-powered applications.
Task statements
- 2.1
Tool Interface Design
Tool descriptions are the primary mechanism LLMs use for tool selection. Minimal descriptions such as "Retrieves customer information" cannot separate overlapping tools, so the first fix is to expand those descriptions.
- 2.2
Structured Error Responses
When an MCP tool fails, a generic message such as "Operation failed" gives the agent nothing to recover from. Execution errors return isError: true with structured metadata so the agent can tell a transient failure from a valid empty result.
- 2.3
Tool Distribution & Tool Choice
How many tools an agent can see is an architectural decision. Eighteen tools on one agent degrade selection. The workable range is 4-5 tools scoped to the agent's role, with near-duplicates collapsed into one parameterised tool.
- 2.4
MCP Server Integration
MCP servers connect Claude to databases, APIs, development tools, and issue trackers. Project-level .mcp.json is version-controlled and shared; user-level ~/.claude.json is personal. Credentials use ${ENV_VAR} expansion, community servers come before custom builds, resources catalogue available data, and rich tool descriptions keep MCP tools competitive with built-ins.
- 2.5
Built-in Tools
Claude Code's six built-in tools are Read, Write, Edit, Bash, Grep, and Glob. Grep searches file contents; Glob matches file paths. Edit is the default modification. When Edit cannot find a unique anchor, the exam answer is Read + Write, while current Claude Code first widens old_string or uses replace_all.