Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive, and the description adds a list of included stats but no further behavioral context like error cases or return format beyond what the output schema likely covers.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.