Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=false, destructiveHint=false, so the safety profile is structured. The description contributes nothing beyond that: it does not state what is aggregated, over what time window, per account, or how the summary is computed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.