Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the description's 'fetches' aligns without adding safety info. It does add the cost ($0.001 USDC) which is beyond annotations, but it does not disclose other behaviors like data freshness, rate limits, or the nature of 'flight safety clearances.' With annotations covering the safety profile, this adds modest value but is not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.