Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered by structured data. The description adds nothing beyond them – it does not state irreversibility, permission requirements, or what happens to associated fine-tuning jobs, which is the kind of context that would earn credit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.