Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive hints. The description adds valuable operational context: 'Free, sub-second, no auth' and the 60+ country coverage, which go beyond the structured annotations. No contradiction with annotations exists.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.