Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must provide all behavioral context, but it only states that it 'gets detailed information'. It does not disclose what the information includes, whether it is a read-only operation, if it has side effects, performance implications, or what the return format is. Thus, the description lacks transparency about the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.