Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the tool is safe to call. The description adds that it's public data with no key needed, which is useful beyond annotations, and highlights its role as a leading indicator. However, it doesn't disclose the exact data source publication date or potential delays.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.