In previous chapters, we focused on the foundational aspects of LLM agents, including their core reasoning capabilities driven by the Large Language Model. While these agents can understand instructions and generate human-like text, their ability to interact with external systems, access real-time information, or perform specific computations is inherently limited. This chapter addresses how to expand these capabilities by "equipping agents with tools."

Throughout this chapter, you will learn to:

• Define what tools are in the context of LLM agents and understand their function.
• Recognize why tools are necessary for agents to accomplish a broader set of tasks effectively.
• Design and implement a basic tool, using a calculator as a practical example.
• Integrate custom or pre-existing tools into your agent's operational structure.
• Modify agent prompts to guide them in using available tools.
• Understand the logic agents employ to decide when and which tool to use.
• Identify common categories of tools frequently used with LLM agents, such as search functionalities or code interpreters.

By the end of this chapter, you will complete a hands-on exercise to add a web search tool to an agent, enabling it to fetch external information.