> For the complete documentation index, see [llms.txt](https://docs.skyone.cloud/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.skyone.cloud/english/skyone-studio/artificial-intelligence/voxone/tools-in-voxone.md).

# Tools in VoxOne

Tools allow AI agents to access external functionalities, APIs, and resources from the platform itself, expanding what the agent can do during a conversation.\
In practice, tools work similarly to traditional agent skills: they enable fetching external information, executing specific actions, and personalizing the user experience.

**How to navigate:**

1. When accessing Skyone Studio, click on **VoxOne**.
2. Click the **Tools** tab.
3. On this screen, you will see:

* Custom tools created by you.
* Platform default tools (identified by a globe icon).

<figure><img src="/files/RRRzuFLmC1ovbe2K2GcB" alt=""><figcaption></figcaption></figure>

***

#### Creating a Custom Tool

Custom tools allow you to integrate the agent with external services, such as APIs. Step by step:

**Main settings**

1. Click **Create new tool**.
2. Define the tool name.
3. Write a description for the tool.

{% hint style="warning" %}
**Attention!** The model will see the tool name and description and will use this information to determine when to make a tool call.
{% endhint %}

**Integration**

1. Choose the **HTTPS** type.
2. Configure the API URL (it may contain dynamic parameters).
3. Select the HTTP method:

* GET
* PUT
* POST
* PATCH

4. Define the timeout to prevent the platform from becoming unresponsive if the API does not respond.

{% hint style="info" %}
A **“Pre-computable”** flag will be available. This flag allows the tool to be executed simultaneously with the agent’s speech. Use it only for read-only operations, such as **GET**, that do not modify data.
{% endhint %}

***

#### Configuring Tool Parameters

Parameters allow the value sent to the API to vary with each use.

Fill in the following fields:

* **Type**
  * **Dynamic:** Always changes
  * **Static:** Remains fixed
  * **Automatic:** The agent determines whether it is dynamic or static
* **Parameter name:** Must match exactly the key name.
* **Method:**
  * Query
  * Patch
  * Header
* **Schema type:**
  * Text
  * Number
  * Integer
  * Boolean
  * Custom
* **Write a description**.

Dynamic parameters allow the agent to use different values in each interaction.

<figure><img src="/files/lEqGm1FjW3YpGsN9U8rI" alt=""><figcaption></figcaption></figure>

***

#### Advanced Settings

Define the agent’s final behavior, choosing one of the following:

* Default
* Speak
* Listen
* Speak once

There will be a **“Static response”** flag, where the tool will always return the same predefined response when the flag is enabled.

<figure><img src="/files/2o4ynGveLTm2jKW277hL" alt=""><figcaption></figcaption></figure>

After saving, the settings will be ready for testing.

***

#### Testing the Tool

1. Click **Test**.
2. Send a JSON with the configured parameter.

**Example:**

```json
{
  "CEP": "01000-000"
}
```

3. Run the test.
4. Check whether the API returns the expected information.

If the test returns correctly, the tool is ready for use.

***

#### Linking the Tool to an Agent

1. Access the desired agent.
2. Go to the agent’s **Tools** section.
3. Select the created tool.
4. Save the changes.

<figure><img src="/files/YJvGdO3hPe6AcgIe7yu2" alt=""><figcaption></figcaption></figure>

From that point on, the agent will be able to access the external API during the conversation.

### FAQ

<details>

<summary><strong>What are tools used for?</strong></summary>

They allow the agent to access external APIs, execute specific actions, and personalize interactions.

</details>

<details>

<summary><strong>What is the difference between a custom tool and a standard tool?</strong></summary>

Custom tools are created by the user. Standard tools are preconfigured and provided by the platform.

</details>

<details>

<summary><strong>Can I use dynamic parameters in any tool?</strong></summary>

Yes, as long as the API supports variable parameters.

</details>

<details>

<summary><strong>Is it mandatory to test the tool before using it in an agent?</strong></summary>

Yes. Testing ensures that the integration is working correctly.

</details>


---

# 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://docs.skyone.cloud/english/skyone-studio/artificial-intelligence/voxone/tools-in-voxone.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.