Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full responsibility for behavioral disclosure. It only states 'test' without explaining side effects (e.g., sends a test payload, logs activity, requires permissions) or expected outcomes (e.g., success/failure response). This is insufficient for safe invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.