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

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

How do you prevent a user from using your "Search Tool" to look up internal sensitive data they shouldn't have access to?

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?