How does an LLM decide which tool to call? If you give a model 50 tools, what happens to its accuracy and context window?

If you need a structured response (like a JSON object), would you rather use a "System Prompt instruction" or the model's native "Function/Tool Calling" capability? Why?

In an API inference call, what is the functional difference between the System, User, and Assistant roles?

LLMs are notoriously bad at following "Write exactly 100 words." How would you design a workflow to strictly enforce a character or word limit?