agent-tool-builder
工具是 AI 智能体与世界交互的方式。设计良好的工具，决定了智能体是正常工作，还是产生幻觉、静默失败，或消耗比必要多 10x 的词元。本技能涵盖从模式到错误处理的工具设计。JSON Schema 最佳实践、真正有助于 LLM 的描述撰写、验证，以及正成为 AI 工具通用语的新兴 MCP 标准。关键洞见：工具描述比工具实现更重要。
机器翻译查看英文原文
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 implementa
适用对象：学习与科研。自动收录 · 待核查。
原作者说明节选
从固定版本的 SKILL.md 提取，保留原文语言。以下内容属于作者说明，本站尚未验证安装、兼容或运行结果。
查看英文原文
原文涵盖的主题
- Agent Tool Builder
- Capabilities
- Patterns
- Tool Schema Design
- Tool with Input Examples
- Tool Error Handling
- Anti-Patterns
- ❌ Vague Descriptions
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 agent-tools function-calling tool-schema-design mcp-tools tool-validation tool-error-handling Creating clear, unambiguous JSON Schema for tools Using examples to guide LLM tool usage Returning errors that help the LLM recover Works well with: multi-agent-orchestration, api-designer, llm-architect, backend
- 来源仓库
- davila7/claude-code-templates
- 源文件
- cli-tool/components/skills/ai-research/agent-tool-builder/SKILL.md
- 固定版本
- 21be197f100a12b8d0dd9a211cc244c8179f84d3
来源与内容状态
本条为自动发现的元数据，尚未完成人工文档核查；适用性与运行结果待核查。
原作者：davila7/claude-code-templates · 原作者仓库元数据。文档核查：未核查。最近来源检查：2026-11-09T14:01:42.953Z。
分类由名称、说明与路径规则生成，分类不代表已核实适配。
许可与权利归属
MIT。第三方内容及版权归原作者，使用条件以原文为准。
许可原文 ↗本站没有因同步、复制或用户自报成功而将资源标为运行验证通过。
限制与注意事项
- 元数据收录不代表本站已经安装、适配、实测或进行安全审查。