# Tools you can give to agent

### Why Tools Matter for AI Agents

AI alone isn't enough—especially in a company context. Without the right tools, even the smartest agent can get overwhelmed, give vague results, or miss the point entirely.

That’s why in Calk AI, every agent can be equipped with specific tools. These tools act like extensions of the agent’s abilities, allowing it to do more than just chat—like browsing the web, analyzing data, scraping content, or even interpreting code.

#### Why It Matters

Imagine asking an agent to:

* Visualize sales data,
* Search the web for market trends,
* Summarize an RSS feed from your industry,
* Analyze a CSV file,
* Or scrape a competitor’s pricing page...

Without the proper tool, the agent will either guess, stall, or deliver something incomplete.

By assigning tools to your agents, you:

* **Avoid messy, unstructured results**
* **Control the agent’s scope** based on your needs
* **Let the agent choose the right tool at the right moment**\
  (Just like a real teammate would.)

#### Tools Available in Calk

Your agents can be equipped with a growing list of tools like:

* [**Web scrape**](/agents/tools-you-can-give-to-agent/web-scrape.md)
* [**Reasoning capacities**](/agents/tools-you-can-give-to-agent/reasoning-capacities.md)
* [**Web search**](/agents/tools-you-can-give-to-agent/web-search.md)
* [**CSV analysis**](/agents/tools-you-can-give-to-agent/csv-analysis.md)
* [**Data visualization**](/agents/tools-you-can-give-to-agent/data-visualization.md)
* [**Code interpreter**](/agents/tools-you-can-give-to-agent/code-interpreter.md)
* [**RSS feed reading**](/agents/tools-you-can-give-to-agent/rss-feed.md)

Each agent doesn’t need every tool—just the ones relevant to their mission. You stay in control, and the agent stays efficient.

***


---

# 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://docs.calk-ai.com/agents/tools-you-can-give-to-agent.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.