Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the read-only nature is known. The description adds the behavioral nuance that only 'top-level' comments are returned, which is useful context. However, it does not disclose behavior around pagination, sorting, or how the status filter affects results, so the added value is limited.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.