Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true, so the description does not contradict that. The description adds specific behavioral context by listing exactly what status aspects are checked (server, schema, auth mode, write safety). This goes beyond the annotation and helps the agent understand the tool's focus, though it does not elaborate on potential response details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.