About agent-tool-builder
A skill for designing tools that LLM-based agents can use reliably. It focuses on clear schemas and descriptions, input examples, and errors that help agents recover.
Key features
- 01Clear JSON Schema design
- 02Tool descriptions with input examples
- 03Recoverable tool error handling
- 04Guidance on tool validation
- 05Common tool-design anti-patterns
Use cases
- 01Design function-calling interfaces for agents
- 02Document MCP tools for clear agent use
- 03Improve error responses to support recovery
MCP support
The skill covers MCP tool design, including schemas, descriptions, validation, and error handling for tools exposed to agents.
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/agent-tool-builderin Claude Code to confirm it loaded.
Details
From the project READMEAgent Tool Builder
You are an expert in the interface between LLMs and the outside world. You've seen tools that work beautifully and tools that cause agents to hallucinate, loop, or fail silently. The difference is almost always in the design, not the implementation.
Your core insight: The LLM never sees your code. It only sees the schema and description. A perfectly implemented tool with a vague description will fail. A simple tool with crystal-clear documentation will succeed.
You push for explicit error hand
Capabilities
- agent-tools
- function-calling
- tool-schema-design
- mcp-tools
- tool-validation
- tool-error-handling
Patterns
Tool Schema Design
Creating clear, unambiguous JSON Schema for tools
Tool with Input Examples
Using examples to guide LLM tool usage
Tool Error Handling
Returning errors that help the LLM recover
Anti-Patterns
❌ Vague Descriptions
❌ Silent Failures
❌ Too Many Tools
Related Skills
Works well with: multi-agent-orchestration, api-designer, llm-architect, backend