Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered by structured data. The description adds the 'soft deletes' nuance, which is useful, but does not explain what soft deletion means for downstream references or whether it is reversible.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.