Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description alone must convey behavioral traits. It only states it 'reads' and optionally includes runs, but it does not disclose any side effects, permissions required, behavior on missing goal, or rate limits. The agent lacks crucial information about safety or requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.