Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful deprecation/aliasing context that annotations cannot express, but says nothing about whether the alias is behaviorally identical, still maintained, or subject to removal, so it only partially earns credit above the annotation baseline.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.