Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and other safety traits. The description adds minimal behavioral context beyond stating 'by country', which is misleading because the input schema has no country parameter. This could confuse the agent about required inputs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.