AG-005Agent · Using toolslayaeval.ToolSelection
Tool Selection
Which tool is the best one for this step?
Simulation state:
When it passes
Picks search.
Threshold satisfied: evaluation score >= 0.70.
When it fails
Picks email.
Violation detected: execution flagged for human review or fallback routing.
SDK Specification
| Parameter | Value | Description |
|---|---|---|
| Class | ToolSelection | Python evaluator class in layaeval |
| Required Fields | "task", "available_tools", "selected_tool" | Arguments expected in the call signature |
| Default Threshold | >= 0.70 | Passes when quality score is at or above this value |
| Category | Agent Evaluation | Using tools (Right tool, right inputs, results actually used.) |
Python Example
tool-selection.py
1from layaeval import ToolSelection23metric = ToolSelection(threshold=0.70) # passes at or above 0.7045res = metric(6 task="Book a hotel in Paris for 2 guests on Mar 4.",7 available_tools=["search_hotels", "calculator", "send_email"],8 selected_tool="search_hotels",9)1011print(res.passed, res.value, res.confidence)
Related Agent Checks
Other checks in Using tools
AG-006Read →
Tool Selection Correctness
Was the tool the agent picked the right one?
AG-007Read →
Tool Call Accuracy
Was the tool called the right way?
AG-008Read →
Tool Input Accuracy
Are the values sent to the tool correct?
AG-009Read →
Tool Output Use
Did the agent use what the tool gave back?
AG-010Read →
Tool Necessity
Was calling a tool really needed here?