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?

Why are delimiters like ###, """, or <xml> tags important in long prompts? How do they help prevent the model from getting confused between instructions and data?

Instead of one giant 2,000-word prompt, why might you split a task into smaller, sequential prompts?

A large prompt (10k tokens) is being sent every time a user asks a simple "Yes/No" question. How would you optimize this to save 90% of your API costs?