Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations (readOnlyHint, idempotentHint, destructiveHint) already disclose the safety profile. The description adds nothing behavioral beyond the endpoint, and does not mention response behavior, caching, or any special conditions. Since annotations carry the burden, the description contributes no extra value there.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.