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 description's job is lighter. It adds real behavioral value by naming the five possible outcome statuses (exact, alias, ambiguous, not_found, withdrawn) and the returned candidates and identity_snapshot_id, telling the agent to expect non-exact resolutions rather than a boolean hit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.