Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds nothing about search behavior, matching semantics, pagination, or result limits, so it contributes no behavioral context beyond the title.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.