Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint, openWorldHint, and destructiveHint annotations already cover safety, so the bar is lower. The description adds useful behavioral context: the response includes life_in_days with age/day_number, similar people, birthday peers, and timeline events including day_number. It also discloses a $0.05 cost, which is beyond what annotations provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.