Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate readOnlyHint=false, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds no behavioral context beyond these hints—it merely repeats the name. It doesn't explain what happens to existing data, whether the update is partial or full, or any side effects. Since annotations already carry some safety hints, the description could compensate with useful details but doesn't.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.