Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations present, the description carries the full burden and it clearly states 'Read-only,' which is useful safety-relevant behavioral information. However, it does not disclose what the summary contains, whether it reflects live data, or any other behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.