langchain-tool-builder

LangChain Tool Builder

Helps define LangChain (Python) tools using Claude Code's buildTool() pattern: a unified class that co-locates identity, schema, security properties, and execution logic, with fail-closed defaults so new tools are safe by default.

Why this pattern matters

Claude Code enforces three things that vanilla LangChain tools lack:

1. Fail-closed defaults — is_read_only, is_destructive, is_concurrency_safe all default to False. A tool that forgets to declare its properties is conservatively treated as write-capable.
2. Layered execution — validate_semantics → check_permissions → _call are separate methods, so validation logic doesn't bleed into permission logic or business logic.
3. Self-contained definition — schema, description, security metadata, and execution all live in one class. No separate permission middleware to wire up.

Workflow

Step 1 — Install the base class

Check if claude_style_tool.py exists in the project's utils directory. The expected location for the ai-base project is: /Users/jigege/ai-base/backend/base/utils/claude_style_tool.py

If it doesn't exist, copy it from references/claude_style_tool.py in this skill directory. Tell the user where it was placed and what it provides.

If working in a different project, ask the user where their utils/tools directory is.

Step 2 — Interview the user

Collect answers to these questions. Defaults are shown — skip questions where the default is clearly fine.

Naming convention: use {service}_{action}_{resource} format with a service prefix so the tool stays unambiguous when multiple tool sets are loaded simultaneously (e.g. stock_get_price, stock_list_symbols, github_create_issue). Start with a verb: get, list, search, create, delete.

Field	Question	Default
name	工具名（格式：{service}_{action}_{resource}，例如 stock_get_price）	— required
description	给 LLM 看的一句话描述：精确匹配实际功能，不要模糊扩大，否则 agent 会在不该用的场景误调用	— required
Schema fields	工具接受哪些参数？（字段名、类型、说明；在 Field description 里加 example，如 e.g. '2024-01-01'）	— required
is_read_only	这个工具只读数据，不写入/不产生副作用吗？	False
is_destructive	这个工具会做不可逆操作（删除、覆盖）吗？	False
is_concurrency_safe	这个工具可以和其他工具同时运行吗？	False
response_format	返回数据是给 agent 程序化处理（JSON）还是给用户展示（Markdown）？	视场景，默认 Markdown
是否列表工具	如果返回多条记录，要支持分页吗？	超过 50 条建议加
_validate_input_semantics	有没有需要在执行前拦截的语义问题？（如：参数太短、路径格式不对）	不需要
_check_permissions	有没有需要检查的权限？（如：只允许读特定路径、需要某个 env var）	不需要
_call	工具的核心执行逻辑是什么？	— required