Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description must carry the burden of behavioral disclosure. It only says 'soft-delete', implying reversibility, but does not explain what that means in practice (e.g., whether the model can be restored, or if there are cascading effects on related data). This is insufficient for a write operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.