Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds genuinely non-obvious behavioral context: slug and revision_id must match, a mismatched pair returns NOT_FOUND, and revision ids are not probeable across pages. This materially changes how the tool can be used.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.