Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds behavioral specifics beyond these: returns up to 5 results, filters by active status, and describes the similarity algorithm. This enhances understanding without contradicting annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.