Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true, and destructiveHint=false, covering the basic safety profile. The description adds nothing beyond that — no mention of required auth, what a 'type' entails, whether value is stored encrypted, or what happens on name collisions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.