ToolCorrectnessScorer
Evaluates if tools were used correctly according to their specifications. Checks for proper parameter types, required fields, and valid value ranges. Compares actual tool calls against expected tool call patterns.
Overview
Evaluates if tools were used correctly according to their specifications. Checks for proper parameter types, required fields, and valid value ranges. Compares actual tool calls against expected tool call patterns.
Use Cases
- Autonomous AI agent evaluation
How It Works
This scorer uses LLM-as-Judge technology to evaluate responses. It prompts a large language model with specific evaluation criteria and the content to assess, then analyzes the LLM's judgment to produce a score and detailed reasoning.
Input Schema
| Parameter | Type | Required | Description |
|---|---|---|---|
| agent_data.expected_tool_call | ToolCall | str | Yes | The expected tool call to compare against |
| agent_data.tool_calls | list[ToolCall] | str | Yes | List of tool calls made by the agent |
Output Schema
| Field | Type | Description |
|---|---|---|
| score | float | Score (0-10 scale) |
| passed | bool | True if score meets threshold |
| reasoning | str | Detailed evaluation explanation |
| metadata | dict | Scorer-specific details |
Score Interpretation
Default threshold: 7/10
Related Scorers
ParameterCorrectnessScorer
Assesses the accuracy and appropriateness of parameters passed to tools. Verifies that parameter val...
AgentToolRelevancyScorer
Evaluates whether the agent selected appropriate tools for the given task. Assesses if the chosen to...
AgentRoleAdherenceScorer
Assesses how well the agent adheres to its defined role and persona throughout the conversation. Eva...
AgentContextRelevancyScorer
Evaluates how well the agent maintains and utilizes relevant context throughout the interaction. Ass...
Frequently Asked Questions
When should I use this scorer?
Use ToolCorrectnessScorer when you need to evaluate agent and tool-usage aspects of your AI outputs. It's particularly useful for autonomous ai agent evaluation.
Why doesn't this scorer need expected output?
This scorer evaluates quality aspects that don't require comparison against a reference answer. It uses the system prompt and context as the implicit ground truth.
Can I customize the threshold?
Yes, the default threshold of 7 can be customized when configuring the scorer.
Quick Info
Ready to try ToolCorrectnessScorer?
Start evaluating your AI agents with Noveum.ai's comprehensive scorer library.
Explore More Scorers
Discover 106 calibrated LLM-as-Judge scorers for comprehensive AI evaluation