Build a Local AI Agent in Python with Tools (Part 3)

Part 3 of a series on building a local AI agent in Python, focused on implementing tool calling — the feature that distinguishes a true AI agent from a chatbot. Covers building a Tools dataclass that converts Python type annotations into JSON schemas for LLMs, registering and executing tools, and implementing the full agent loop where the model can call tools, receive results, and generate a final response. Demonstrates with simple math and secret-key tools using a local Qwen model via LM Studio, and discusses best practices like keeping tools simple and adding loop limits.