Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide strong safety signals (readOnlyHint, idempotentHint, destructiveHint=false). The description adds the HTTP GET method, which is consistent with these hints but does not disclose additional behavioral details such as error handling, return format, or edge cases. With annotations present, the description adds modest value beyond them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.