Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare openWorldHint=true, destructiveHint=false, and readOnlyHint=false, covering much of the safety profile. The description adds that results include uncertainty bands and are bounded to 1-15 day horizons, which is useful output context. It says nothing about data freshness, as_of_date semantics, or any cost/rate behavior though.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.