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 behavior beyond that by enumerating what the caller receives (address, hours, services, and practical tips for 90-day reports, extensions, TM30), which substitutes for the missing output schema; it does not cover data freshness, multiple offices per city, or result ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.