Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. 'Deletes' implies a destructive action, but it does not disclose whether the deletion is permanent, cascades to associated content (e.g., messages, members), or requires special permissions. This lacks context beyond the basic operation, similar to the update_drive calibration example.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.