Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It does disclose a meaningful trait: the reply is 'moderated.' However, it does not mention the one-time-only nature, mutability, permissions, or what happens after moderation; those details are left to the schema and output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.