Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool as read-only, idempotent, and non-destructive, so the description's addition of 'returns events with timestamps, properties, and interactions' adds some value by hinting at the output structure. However, it does not disclose pagination behavior, authentication requirements, or the fact that it uses an internal user ID from amp_user_search.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.