Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the tool is destructive ('deletion') and that it returns a short-lived token, implying the action is not immediate and requires confirmation. This is good transparency for a simple tool, though it could mention that the database is not actually dropped until confirmation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.