You are designing a virtual assistant that helps users check weather updates via external APIs.

The high-value engineering move is wrappers that convert messy external services into stable functions with bounded latency and predictable failure semantics. At production scale, Option D preserves separability between reasoning, state, tools, and runtime operations. Few-shot tool examples constrain the model’s action format. For weather APIs, schema examples prevent fabricated endpoints, missing parameters, and invalid response shapes. For a production build, tool execution should sit behind adapters that can be profiled and regression-tested just like retrieval and inference services. The selected option specifically D states “Use structured prompt templates with few-shot tool usage examples”, which matches the operational requirement rather than a superficial wording match. The rejected options are weaker because hardcoded endpoints, loose parsers, or monolithic handlers turn every API change into an application release and hide failures from observability. Anything less would make the agent fragile when traffic, schemas, policies, or user behavior shift. Schema validation, typed return objects, and trace IDs also make post-incident debugging realistic when a third-party dependency changes behavior.