Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full behavioral disclosure burden but fails to specify return value structure, error handling (e.g., 404 for invalid ID), permission requirements, or whether sensitive fields like passwords/tokens are returned. Only states the obvious read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.