agent-tool-builder

Installation
Summary

Design LLM-facing tool schemas that prevent hallucination, silent failures, and token waste.

  • Focuses on JSON Schema design, input examples, and error handling patterns that help LLMs use tools correctly
  • Emphasizes explicit documentation and clear descriptions over implementation details, since LLMs only see the schema
  • Identifies anti-patterns like vague descriptions, silent failures, and tool overload that cause agent failures
  • Covers function-calling, MCP tools, and tool validation across agent-tool ecosystems
SKILL.md

Agent Tool Builder

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary.

This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools.

Key insight: Tool descriptions are more important than tool implementations. The LLM never sees your code - it only sees the schema and description.

Principles

  • Description quality > implementation quality for LLM accuracy
  • Aim for fewer than 20 tools - more causes confusion
  • Every tool needs explicit error handling - silent failures poison agents
  • Return strings, not objects - LLMs process text
Related skills
Installs
616
GitHub Stars
37.3K
First Seen
Jan 19, 2026