If you're building AI agents that actually work, this is about the unsexy part that matters most: tool design. The core insight is right on,LLMs never see your implementation, only your schema and descriptions, so a perfectly coded tool with vague docs will fail while a simple one with clear documentation succeeds. Covers JSON Schema best practices, description writing that helps instead of confuses, validation patterns, and MCP (the emerging standard for AI tools). The focus on explicit error handling is especially good since most agent failures happen when tools return garbage and the LLM has no idea what went wrong. Think of this as the missing manual for function calling that actually prevents hallucinations and token waste.
npx skills add https://github.com/davila7/claude-code-templates --skill agent-tool-builder