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. However, the description adds no behavioral context such as what the returned list contains, whether pagination is supported, or any filtering nuances. With the bar lowered by annotations, this still falls short because it contributes no additional behavioral detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.