Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds the useful hint that output is intended as slugs for a downstream call, but says nothing about result format, empty-query behavior, or ranking beyond what the schema states. Adequate, not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.