Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile and indicating an open-world read. The description adds almost nothing beyond that: it does not explain caching (despite the 'fresh' parameter), permissions, return format, or what 'open in the panel tab' means behaviorally. With annotations carrying the safety burden, the description should still add context but does not.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.