Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it references live delivery-quote / DHRC and 'fails closed when that container cannot serve the ZIP,' which is meaningful failure-mode transparency. It could say more about latency or quota, but this is solid.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.