Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true and idempotentHint=true, telling the agent this is a safe, read-only, idempotent operation. The description adds the verb 'Read', which is consistent but does not add further behavioral details (e.g., behavior when sessionId is invalid). With annotations covering the key traits, the description provides minimal incremental value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.