Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Even though an output schema exists, the description provides no context about the tool's operation, side effects, or requirements. For a mode-changing tool, an agent would need to know what 'edit mode' entails (e.g., it affects the active mesh object), or at least that the object must be a mesh. The complete lack of context makes this tool unsafe to invoke reliably.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.