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 useful behavioral context by noting all parameters are optional and can be combined to narrow results. It does not disclose behavior like pagination or result limits, but those are largely optional given the strong annotation coverage and output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.