Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description still adds real behavioral value: it discloses that DRAFT (unpublished) streams are included in the result set, which an agent would not infer from the annotations or the streamState enum alone — though it says nothing about result ordering beyond the schema's sortBy docs or about pagination semantics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.