Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description must bear the full burden of behavioral disclosure. It merely says 'Toggle fullscreen' but does not explain the toggling behavior (e.g., from windowed to fullscreen and back), any side effects (e.g., affecting multiple windows), or the existence of the 'mode' parameter. This leaves significant gaps for an AI agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.