Which built-in evaluator suits an agent specifically?
Why C is the answer
Tool call accuracy
Microsoft lists tool call accuracy and task completion as agent-specific metrics.
In detail
- Tool call accuracy looks at how an agent used its tools.
- Evaluate tool use, as well as final answers.
Use case
An illustrative scenario, not a real incident.
An agent picks the wrong tool. Tool call accuracy shows how well it uses tools, which general text evaluators cannot.
See it in different ways
flowchart TD A["Foundry evaluators"] --> B["General: coherence, fluency"] A --> C["RAG: groundedness, relevance"] A --> D["Safety: hate, violence, protected material"] A --> E["Agents: tool call accuracy, task completion"]
mindmap
root((Evaluators))
Quality
Relevance
Coherence
Fluency
RAG
Groundedness
Agents
Tool call accuracy
Safety
Violence
Hate and unfairness
Protected materialsflowchart LR S0["Task"] --> S1["Agent calls tools"] --> S2["Compare with expected"] --> S3["Score"]
Key point: Tool call accuracy suits agents.
Why the other options are wrong
- A. Coherence
- Coherence applies to any text.
- B. Fluency
- Fluency applies to any text.
- D. Hate and unfairness
- That is a general safety evaluator.