Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already carry the important traits: destructiveHint=true, idempotentHint=true, readOnlyHint=false. The description adds nothing beyond them — no note on irreversibility, cascade effects on transcripts/languages, or required permissions. With annotations covering safety, the bar is lower, but zero added context still warrants a low score.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.