Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=false, idempotentHint=true, and openWorldHint=false, so the safety and idempotency profile is largely covered by structured data. The description restates idempotency ('same idempotency key return the same folder') with slightly more concrete wording, but says nothing about permissions needed to create a team-visible folder, name-collision behavior, or limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.