Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior, but it only lists output field names. It does not state whether the tool reads data, requires authentication, has side effects, or what 'is_following' actually refers to (e.g., following the post author). No rate limits, error behavior, or safety profile is mentioned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.