Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as read-only and idempotent, and the description adds substantial behavioral detail: Postgres plainto_tsquery with 'simple' config, non-soft-deleted scoping, membership requirement, and the deprecated alias relationship. It also explains response semantics (items, results, count, has_more).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.