Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only and idempotent, and the description adds meaningful behavioral context: co-op capacities are reported as distinct fields, the result includes source, canonical_url, and UTM-tagged open_url, and the agent should attribute Co-Op Now and include the co-op.now link when links/citations are supported. This goes beyond schema or annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.