Update result key to tool_call_accuracy

Author: Salma Elshafey

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_tool_call_accuracy/_tool_call_accuracy.py

@@ -65,7 +65,7 @@ class ToolCallAccuracyEvaluator(PromptyEvaluatorBase[Union[str, float]]):
     """
 
     _PROMPTY_FILE = "tool_call_accuracy.prompty"
-    _RESULT_KEY = "tool_call_accurate"
+    _RESULT_KEY = "tool_call_accuracy"
 
     _MAX_TOOL_CALL_ACCURACY_SCORE = 5
     _MIN_TOOL_CALL_ACCURACY_SCORE = 1

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_tool_call_accuracy/test_new_evaluator.ipynb

@@ -27,8 +27,8 @@ def test_tool_call_accuracy_evaluator_missing_inputs(self, mock_model_config):
             }]
         )
         assert not result["applicable"]
-        assert result["tool_call_accurate"] == "not applicable"
-        assert "No tool calls found in response or provided tool_calls." in result["tool_call_accurate_reason"]
+        assert result["tool_call_accuracy"] == "not applicable"
+        assert "No tool calls found in response or provided tool_calls." in result["tool_call_accuracy_reason"]
 
         # Test with missing tool_definitions
         result = tool_call_accuracy(
@@ -43,8 +43,8 @@ def test_tool_call_accuracy_evaluator_missing_inputs(self, mock_model_config):
             }]
         )
         assert not result["applicable"]
-        assert result["tool_call_accurate"] == "not applicable"
-        assert "Tool definitions must be provided." in result["tool_call_accurate_reason"]
+        assert result["tool_call_accuracy"] == "not applicable"
+        assert "Tool definitions must be provided." in result["tool_call_accuracy_reason"]
 
         # Test with response that has no tool calls
         result = tool_call_accuracy(
@@ -65,8 +65,8 @@ def test_tool_call_accuracy_evaluator_missing_inputs(self, mock_model_config):
             }]
         )
         assert not result["applicable"]
-        assert result["tool_call_accurate"] == "not applicable"
-        assert "No tool calls found in response or provided tool_calls." in result["tool_call_accurate_reason"]
+        assert result["tool_call_accuracy"] == "not applicable"
+        assert "No tool calls found in response or provided tool_calls." in result["tool_call_accuracy_reason"]
 
         # Test with tool call for which definition is not provided
         result = tool_call_accuracy(
@@ -91,5 +91,5 @@ def test_tool_call_accuracy_evaluator_missing_inputs(self, mock_model_config):
             }]
         )
         assert not result["applicable"]
-        assert result["tool_call_accurate"] == "not applicable"
-        assert "Tool definitions for all tool calls must be provided." in result["tool_call_accurate_reason"]
+        assert result["tool_call_accuracy"] == "not applicable"
+        assert "Tool definitions for all tool calls must be provided." in result["tool_call_accuracy_reason"]