Writing Effective Tools for Agents
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
Collins at p99log pulls together OpenAI, Anthropic, Google and MCP guidance on designing agent tools: build around workflows rather than API endpoints, treat descriptions and errors as prompt text, and avoid overlapping tools. Past about 20 tools, toolsets, tool search or code execution cut context cost; GitHub's server dropped from 101 tools and 64.6k tokens to 52 and 30.3k. Anthropic's figures are from its own tests. Collins adds security advice, including idempotency keys on writes, which is his own recommendation.