Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of disclosing behavior. It only offers 'workload analysis' and gives no information about the return format, read-only nature, or side effects. It does not contradict any annotations, but it reveals almost nothing about how the tool behaves.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.