> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agntix.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Tools

> Extend agent capabilities with API webhook tools and server-side function tools.

**Tools** let your agents take action in the real world. When the LLM decides a tool should be called, Agntix executes it and feeds the result back into the conversation.

There are two tool types:

| Type            | Description                                                    |
| --------------- | -------------------------------------------------------------- |
| `API_TOOL`      | Makes an HTTP request to your webhook URL. No code required.   |
| `FUNCTION_TOOL` | Calls a named server-side function registered in your backend. |

<CardGroup cols={2}>
  <Card title="Create a tool" icon="plus" href="/api-reference/tools/create">
    Define a new API or function tool.
  </Card>

  <Card title="List tools" icon="list" href="/api-reference/tools/list">
    Browse all tools in your organization.
  </Card>

  <Card title="Attach to an agent" icon="robot" href="/api-reference/agents/update">
    Link a tool to an agent using PATCH /v2/chat/agents/{id}.
  </Card>

  <Card title="Test a tool" icon="flask" href="https://app.agntix.ai/tools">
    Use the dashboard playground to test tools before attaching them.
  </Card>
</CardGroup>

## Key concepts

* **`name`** — the function name the LLM sees. Use UPPER\_SNAKE\_CASE for clarity (e.g. `GET_ACCOUNT_BALANCE`). Must be alphanumeric with underscores, no leading/trailing underscores.
* **`description`** — tells the LLM *when* to call this tool. Be specific. The LLM uses this to decide whether to invoke the tool in a given context.
* **`ajvPropertiesSchema`** — a JSON Schema object defining the tool's input parameters. The LLM constructs its call arguments based on this schema.
* **`preExecutionMessage`** — an optional message spoken/sent to the user while the tool runs (e.g. *"Let me look that up for you..."*).

## API tool example

```json theme={null}
{
  "name": "GET_ACCOUNT_BALANCE",
  "description": "Retrieves the account balance for the authenticated customer. Call when the user asks about their balance, account funds, or available credit.",
  "type": "API_TOOL",
  "apiTool": {
    "url": "https://api.acme.com/v1/accounts/{{customerId}}/balance",
    "method": "GET",
    "headers": { "Authorization": "Bearer {{apiKey}}" }
  },
  "ajvPropertiesSchema": {
    "type": "object",
    "properties": {
      "customerId": {
        "type": "string",
        "description": "The customer's unique ID from the session metadata."
      }
    },
    "required": ["customerId"]
  }
}
```

## Tools and agents

A tool must be attached to an agent before it becomes available in conversations. Attach tools via the `tools` array in [Create Agent](/api-reference/agents/create) or [Update Agent](/api-reference/agents/update).