Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete action with a fully documented schema and a destructiveHint annotation, the core invocation information is present. However, the definition lacks any usage alternatives, behavioral warnings, or clarification of what happens when force is false and the collection is non-empty, leaving the agent to infer important operational context on its own.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.