Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple toggle tool with high schema coverage and a single required boolean, the description is largely adequate for invocation. However, with zero annotations, no output schema, and a debug/instrumentation tool that has more behavioral nuance (window persistence, frame effects, whether it modifies UI state), a bit more behavioral context would round it out. A simple toggle arguably doesn't need more, but the debugging nature warrants light additional disclosure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.