# Tools

**Agents use tools to take actions and interact with external systems**.

Tools are functions that an Agent can run to achieve tasks. For example: searching the web, running SQL, sending an email or calling APIs.

## Available Tools and Capabilities

### Tool Categories

#### Time  

* **get\_current\_time**: Get current date and time in specified format
* Use for: Time-based operations and scheduling

#### Calculator

* **calculate**: Perform mathematical calculations
* Use for: Basic arithmetic to complex mathematical operations

#### Finance

* **get\_stock\_price**: Real-time stock market data
* **get\_finance\_news**: Latest financial news
* Use for: Financial analysis and market research

#### Search 

* **web\_search**: General internet search
* **search\_wikipedia**: Wikipedia article lookup
* **search\_arxiv**: Academic paper search
* **search\_youtube**: YouTube video search
* Use for: Comprehensive research and information gathering

#### Language

* **translate\_text**: Text translation
* **summarize\_text**: Text summarization
* Use for: Content processing and language tasks

#### Media 

* **generate\_image**: AI image generation
* **read\_pdf\_url**: PDF document reading
* Use for: Content creation and document analysis

#### GitHub

* **get\_github\_issues**: Fetch repository issues
* **get\_github\_pull\_requests**: Access PR information
* Use for: Code review and project management

### Available Models

#### OpenAI

* **gpt-4o**: Advanced language model for complex tasks
* Best for: Complex reasoning and detailed analysis

#### Anthropic

* **claude-3-5-sonnet-20241022**: Balanced performance model
* Best for: General-purpose tasks and content generation

#### DeepSeek

* **deepseek-chat**: Specialized chat model
* Best for: Conversational interactions

#### Google

* **gemini-1.5-pro**: Advanced reasoning model
* Best for: Multi-modal tasks and complex problem-solving


---

# Agent Instructions: 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:

```
GET https://kidjig.gitbook.io/kidjig-docs/agents-api/tools.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.