Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter tool with an output schema and annotations covering destructive/idempotent behavior, the description is sufficiently complete. It covers purpose, personal scope, and authentication. The only minor gap is that it doesn't explicitly state at least one parameter must be provided, but the schema already conveys that, so the description need not repeat it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.