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.
Profile →npx skills add sickn33/agentic-awesome-skills --skill agent-tool-builder --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides the design of agent tools, focusing on tool schemas, description quality, validation, and error handling. Emphasizes returning strings, strict pre-execution validation, and testing tools with the LLM.
How it works
Outlines principles and capabilities for tool design, including: prioritizing high-quality, unambiguous descriptions over implementation details; aiming for a small set of tools (fewer than 20); requiring explicit error handling for every tool; using JSON Schema and MCP standards; leveraging frameworks like Anthropic SDK, OpenAI Functions, Vercel AI SDK, and LangChain Tools; and applying recommended patterns for tool schema design, parameter descriptions, and input examples. It provides examples and patterns for tool schemas, error handling, and MCP tooling, plus guidance on tool use patterns and parallel execution considerations.
When to use it
Use when constructing new agent tools or refining existing ones to ensure clear descriptions, validated inputs, and robust error handling. Apply when designing tool schemas, enforcing validation gates, and ensuring tools are testable with the LLM.
What it can touch
- Tool schemas and descriptions
- Validation rules and error-handling structures
- Tool lifecycle guidance across MCP, Anthropic SDK, OpenAI Functions, Vercel AI SDK, and LangChain Tools
Caveats
- Declared risk: critical
- License: MIT
- Content focuses on design principles and best practices; actual tool implementations are not provided
# 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 - Validation gates before execution - reject, fix, or escalate, never silent fail - Test tools with the LLM, not just unit tests ## Capabilities - agent-tools - function-calling - tool-schema-design - mcp-tools - tool-validation - tool-error-handling ## Scope - multi-agent-coordination → multi-agent-orchestration - agent-memory → agent-memory-
- Principles
- Capabilities
- Scope
- Tooling
- Standards
- Frameworks
- Patterns
- Tool Schema Design
- 1. Detailed Descriptions (Most Important)
- 2. Parameter Descriptions
- 3. Use Enums When Possible
- 4. Required vs Optional
- Tool with Input Examples
- Tool Error Handling
What does the agent-tool-builder skill do?
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.
How do I install it?
Run `npx skills add sickn33/agentic-awesome-skills --skill agent-tool-builder --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From sickn33/agentic-awesome-skills, a repository with 44,414 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.