> ## Documentation Index
> Fetch the complete documentation index at: https://docs.laragent.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Overview
> Tools extend your agent's capabilities, allowing them to perform actions like calling APIs, querying databases, or executing any custom logic.
Tools (also known as function calling) allow your AI agents to interact with external systems and services, expanding their capabilities beyond text generation. When an LLM needs to perform an action, it calls a tool and uses the result to formulate its response.
## What are Tools?
In LarAgent, a **Tool** is a function or class that an agent can invoke to perform actions or retrieve information. Tools bridge the gap between AI reasoning and real-world operations.
Common use cases include:
* Fetching data from APIs or databases
* Sending emails or notifications
* Performing calculations
* Interacting with external services
When an agent determines it needs information or needs to take action, it calls the appropriate tool, receives the result, and uses it to continue the conversation.
## Creating Tools
LarAgent offers three ways to define tools, each suited for different use cases:
**Recommended.** Transform agent methods into tools with a simple attribute — best for most use cases.
Create reusable tool classes or build tools dynamically at runtime.
### Quick Examples
The simplest approach — add the `#[Tool]` attribute to any method in your agent class:
```php theme={null}
use LarAgent\Attributes\Tool;
#[Tool('Get the current weather for a location')]
public function getWeather(string $location, string $unit = 'celsius'): string
{
return WeatherService::get($location, $unit);
}
```
Create a dedicated class for complex or reusable tools:
```php theme={null}
class WeatherTool extends LarAgent\Tool
{
protected string $name = 'get_weather';
protected string $description = 'Get the current weather for a location';
protected array $properties = [
'location' => [
'type' => 'string',
'description' => 'City and state, e.g. San Francisco, CA',
],
];
public function execute(array $input): mixed
{
return WeatherService::get($input['location']);
}
}
```
Build tools dynamically using the fluent API:
```php theme={null}
use LarAgent\Tool;
Tool::create('get_weather', 'Get the current weather')
->addProperty('location', 'string', 'City name')
->setCallback(fn($location) => WeatherService::get($location));
```
## Tool Execution Flow
When an agent uses tools:
The LLM analyzes the conversation and determines a tool call is needed.
LarAgent automatically executes the requested tool with the provided arguments.
The tool's return value is sent back to the LLM as context.
The LLM uses the tool result to formulate its final response.
LarAgent handles the entire tool execution loop automatically — you just define your tools and the agent does the rest.
## Next Steps
Learn how to create tools using the #\[Tool] attribute on agent methods.
Build reusable tool classes or create tools dynamically.
Get type-safe responses using DataModels and schemas.