Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide no hints (no readOnlyHint or destructiveHint). The description adds no behavioral details beyond the name itself—e.g., it does not state that this is a read-only operation, that it returns the full tree or a subset, or whether it works only on running games. This lack of disclosure leaves the agent uninformed about invocation consequences.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.