# OpenCode Features and Practical Usage 🧰 When the built-in tools aren't enough and you need to hit an internal API or DB, you can give the LLM its own purpose-built tool. 🏷️ Title: Custom Tools 🔗 URL: 📘 Overview Custom tools are your own functions that the LLM can invoke autonomously during a conversation. They extend the built-in tools (read/write/bash) so the agent can perform domain-specific operations like internal API access or database queries. Definitions are written in TypeScript/JavaScript, but the implementation can shell out to any language. ⚙️ How It Works ・Two locations: `.opencode/tools/` for project-scoped tools, or `~/.config/opencode/tools/` for global ones. ・The filename becomes the tool name. `database.ts` creates a `database` tool. ・You can define multiple tools per file via named exports, which become `_`. ・Define tools with the `tool()` helper from `@opencode-ai/plugin`. The core fields are `description` (what the LLM sees), `args` (a Zod schema), and `execute` (the async implementation). ・Arguments are type-safe via Zod. Use `tool.schema` or import `zod` directly. ・The second argument to `execute` is a context object exposing session info: `agent`, `sessionID`, `messageID`, `directory`, and `worktree` (the git root). 🛠️ Practical Usage Minimal example at `.opencode/tools/database.ts`: a default-exported `tool()` with a `description`, an `args` Zod schema (e.g. a `query` string), and an async `execute` that runs the query and returns the result. The body can call any language. For instance, build a script path from `context.worktree` and run it with `Bun.$`python3 ...``. 💡 Use Cases Define a tool that hits your internal inventory API or an authenticated internal endpoint, and the agent can fetch or update internal data just like it uses built-in tools. The more carefully you write the `description`, the better the LLM picks the right moment to call it. ⚠️ Caveats ・A custom tool with the same name as a built-in one overrides it. Unless you mean to replace it, use unique names. If you only want to disable a built-in tool, `deny` it via permissions instead of overriding. ・Since `execute` may run external commands or internal APIs, be careful with execution rights and secret handling. #OpenCode# #AIAgents#