Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds that no template selection is possible, but for a destructive-flagged tool it says nothing about whether the current document is discarded, whether unsaved work is affected, or whether the new assembly becomes active.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.