How do you evaluate an agent when the "correct path" might involve 5 different tool calls in any order?

How does the model actually "call" a tool? Explain the back-and-forth between the Assistant message and the Tool/Function message in an API loop.

How does the "Extraction, Transformation, and Loading" process differ when preparing data for a Vector Database versus a traditional SQL database?

If a tool returns a massive 50MB JSON file, you can't feed that to the LLM. How do you "summarize" or "filter" tool observations for the agent?