Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. The description adds return field details (citing/cited DOI pair, creation date, self-citation flag) and explains the OCI format. It does not cover error behavior, but the annotations sufficiently cover safety traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.