Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering safety and mutation. The description adds no behavioral details beyond what's in the schema (e.g., return fields). With rich annotations, the description adds minimal value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.