Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and readOnlyHint=false, so the description carries less burden. It adds meaningful context beyond annotations by noting cancellation only works pre-completion, which is a behavioral constraint not evident from schema or annotations. No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.