Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral details beyond annotations: 'signed', 'midnight to midnight', 'endpoints exclusive'. Annotations already indicate read-only, idempotent, non-destructive; description enriches with exact calculation semantics. No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.