Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true, so the agent knows it's read-only. The description adds 'detailed information' but does not disclose further behavioral traits (e.g., response size, permissions, data freshness). With annotations covering safety, the description adds limited context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.