Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds valuable behavioral details beyond annotations: 'Fuzzy-search' indicates approximate matching, 'Keyless' indicates no authentication required, and it lists returned fields (name, type, category, description). These are useful nuances not present in the schema or annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.