Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, idempotentHint=true, readOnlyHint=false. The description adds genuinely new behavioral context: presentations are preserved, and their internal links dangle afterwards. That surviving-side-effect detail is exactly what annotations cannot express.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.