AG-009Agent · Using toolslayaeval.ToolOutputUtilization

Tool Output Use

Did the agent use what the tool gave back?

Simulation state:

When it passes

Results flow into the answer.

Threshold satisfied: evaluation score >= 3.0.

When it fails

Most results dropped.

Violation detected: execution flagged for human review or fallback routing.

SDK Specification

Parameter	Value	Description
Class	ToolOutputUtilization	Python evaluator class in layaeval
Required Fields	"task", "tool_output", "subsequent_actions", "final_response"	Arguments expected in the call signature
Default Threshold	>= 3.0	Passes when quality score is at or above this value
Category	Agent Evaluation	Using tools (Right tool, right inputs, results actually used.)

Python Example

pip install layaeval

tool-output-use.py

1from layaeval import ToolOutputUtilization
2
3metric = ToolOutputUtilization(threshold=3.0)  # passes at or above 3.0
4
5res = metric(
6    task="Book a hotel in Paris for 2 guests on Mar 4.",
7    tool_output="[{id: 12, name: 'Hotel Lumière', price: 180}]",
8    subsequent_actions="book(id=12)",
9    final_response="Booked Hotel Lumière for Mar 4.",
10)
11
12print(res.passed, res.value, res.confidence)