Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a schema-modification tool, the description covers the essential aspects: purpose, destructive nature, confirm requirement, and a specific restriction. The output schema is present, so return values are presumably documented there. It could mention idempotency or the need for a contextRunId in strict mode, but those are secondary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.