Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, idempotentHint, destructiveHint. The description adds valuable behavioral details: returns content and metadata, scoped to the agent, existence not leaked, requires authentication. This goes beyond what annotations convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.