Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Even with annotations already marking destructiveHint=true and readOnlyHint=false, the description adds valuable behavioral detail: soft-delete semantics, movement to the deleted list, restoration via UI, tombstoning of pages, required permission, and the instruction to confirm with the user. This goes well beyond the annotations and gives the agent a clear model of side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.