Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already signal a non-read-only, non-destructive write, and the description adds meaningful behavior beyond that: cross-agent dedup, the nightly sweep over active rows, and active/removed semantics via the stage field. It also discloses the return shape with created/updated/skipped counts. This is a useful, non-contradictory behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.