Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description takes on full responsibility. It explains the output types (net, waste-adjusted, purchase quantities) and notes it's an estimate. However, it does not disclose side effects, permissions, error behavior, or the meaning of 'auditable', leaving some behavioral aspects unclear.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.