Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full disclosure burden but omits critical behavioral details: what 'autoConnect' connects to, what happens when 'timeoutMs' is reached, whether the simulation triggers actual game logic, and what 'additionalProperties: true' implies for action parameters.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.