Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description must carry the burden of behavioral transparency. It states that the tool checks configuration without revealing secrets, implying it is a safe, read-only operation. However, it does not describe what the return value is, whether it can fail, or if it requires any prior setup.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.