> For the complete documentation index, see [llms.txt](https://learn.doubletick.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://learn.doubletick.io/ai-agent/how-to-create-a-new-ai-agent/tools-how-to-give-your-ai-agent-the-ability-to-take-action.md).

# Tools — How to Give Your AI Agent the Ability to Take Action

Without tools, your AI Agent can only reply with text. With tools, it can take action — trigger a Bot Studio journey, fetch data from an external system, or send rich messages like images, buttons, and interactive lists.

Think of tools as skills you give your agent. The more tools you configure, the more your agent can do.

<figure><img src="/files/RhHIxez3lJ7R0Tp8s8Pz" alt=""><figcaption></figcaption></figure>

#### <mark style="color:$primary;">**What You See on the Tools Tab**</mark>

The Tools tab shows all tools configured for your agent.&#x20;

<table><thead><tr><th width="183.00006103515625">Tab</th><th>What It Shows</th></tr></thead><tbody><tr><td><strong>All</strong></td><td>Every tool configured for this agent</td></tr><tr><td><strong>Bot Tools</strong></td><td>Tools that trigger a Bot Studio journey</td></tr><tr><td><strong>API Tools</strong></td><td>Tools that call an external system to fetch or send data</td></tr><tr><td><strong>Send Tools</strong></td><td>Built-in tools for sending rich message types</td></tr><tr><td><strong>MCP Servers</strong></td><td>Advanced integration tools using the Model Context Protocol</td></tr></tbody></table>

There are three main types:

<mark style="color:$primary;">**Bot Tools**</mark> trigger a Bot Studio journey when a customer expresses a specific intent. Use them to collect information, send structured messages, or assign conversations to team members.&#x20;

<mark style="color:$primary;">**API Tools**</mark> call an external system to fetch or send data in real time. Use them to look up customer records, check availability, create leads, or perform actions in a third-party system.

<mark style="color:$primary;">**Send Tools**</mark> are built-in tools for sending rich WhatsApp messages. They work out of the box — no setup required.

<table><thead><tr><th width="184">Send Tool</th><th>What It Sends</th></tr></thead><tbody><tr><td><strong>Image</strong></td><td>An image message</td></tr><tr><td><strong>Document</strong></td><td>A file or document attachment</td></tr><tr><td><strong>Video</strong></td><td>A video message</td></tr><tr><td><strong>Buttons</strong></td><td>A message with up to 3 clickable buttons</td></tr><tr><td><strong>List</strong></td><td>An interactive scrollable list</td></tr><tr><td><strong>Interactive</strong></td><td>A rich message with image header, body text, and reply buttons</td></tr><tr><td><strong>Media Carousel</strong></td><td>2 to 10 swipeable cards with images and CTAs</td></tr></tbody></table>

***

<figure><img src="/files/D00tEezfmqyPmEwB5Gfk" alt=""><figcaption></figcaption></figure>

#### <mark style="color:$primary;">**How to Read the Tools Table**</mark>

Each row in the table represents one tool. Here is what each column tells you:

<table><thead><tr><th width="183">Column</th><th>What It Means</th></tr></thead><tbody><tr><td><strong>Name</strong></td><td>The tool's name with a coloured badge showing its type (Bot, API, Default, or WhatsApp)</td></tr><tr><td><strong>Description</strong></td><td>What the tool does — the AI reads this to decide when to use it</td></tr><tr><td><strong>Parameters</strong></td><td>Input data the tool needs. Shows "No parameters" for simple triggers, or lists the specific fields</td></tr><tr><td><strong>Actions</strong></td><td>Edit (pencil), Journey link (for Bot Tools), Delete (trash), and an enable/disable toggle</td></tr></tbody></table>

***

#### <mark style="color:$primary;">**How to Enable or Disable a Tool**</mark>

<figure><img src="/files/6GQYaNYNP6YzWUUAFk3U" alt=""><figcaption></figcaption></figure>

1. Locate the tool in the table.
2. Click the **toggle on the right side** of that row.
3. **Green toggle = tool is active** and the agent can use it. **Grey toggle = tool is disabled** and the agent will ignore it.

Disable tools you are not currently using rather than deleting them — this keeps your configuration intact for later.

***

#### <mark style="color:$primary;">**How to Edit a Tool**</mark>

<figure><img src="/files/YXTdRQafD31dJY2Tf7RQ" alt=""><figcaption></figcaption></figure>

1. Click the **Edit (pencil)** icon on the tool's row.
2. The form opens pre-filled with the existing configuration.
3. Make your changes.
4. Click **Update** to save.

***

#### <mark style="color:$primary;">**How to Delete a Tool**</mark>

<figure><img src="/files/JDl9KLOrgt4n9VG4k3D8" alt=""><figcaption></figcaption></figure>

1. Click the **Delete (trash)** icon on the tool's row.
2. The tool will be permanently removed.

This cannot be undone.

***

#### <mark style="color:$primary;">**Summary**</mark>

In this article, you learned what tools are, the three types of tools available (Bot, API, and Send), how to read the tools table, and how to enable, disable, edit, and delete tools. In the next article, we will cover Bot Tools in detail — how to create them, add parameters, and build their Bot Studio journeys.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://learn.doubletick.io/ai-agent/how-to-create-a-new-ai-agent/tools-how-to-give-your-ai-agent-the-ability-to-take-action.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.