Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden for a destructive operation. '(gated)' hints at a safeguard but never defines it, and nothing is said about irreversibility, permissions, or the role of the confirm flag. The one behavioral hint is too vague to act on.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.