Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark it read-only, idempotent, and non-destructive, and the description adds useful behavioral context: no API key is needed, calling with null returns a catalog, passing a topic returns a sequence, and every listed tool is invokeable via tools/call. This goes well beyond the structured annotation hints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.