Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, covering the safety profile. The description adds no extra behavioral context, such as what 'associated' means, whether results are flat or nested, or how missing products are handled. It essentially restates the tool name without enriching agent understanding.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.