Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide the basic safety profile (non-read-only, non-idempotent, non-destructive), but the description adds no behavioral context. It does not explain what cancellation does to the plan, whether it is reversible, whether authentication is required, or what side effects may occur. The word 'cancel' is the sole behavioral clue.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.