Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no annotations and no output schema, the description should clarify the operation's effects, such as permanence, success/failure responses, or error conditions. The bare phrase 'Delete a comment' does not provide this, leaving the tool incomplete for an agent to anticipate outcomes.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.