diff --git a/lib/crewai/src/crewai/llms/providers/snowflake/completion.py b/lib/crewai/src/crewai/llms/providers/snowflake/completion.py
index ed2e9c344..f6ecd5010 100644
--- a/lib/crewai/src/crewai/llms/providers/snowflake/completion.py
+++ b/lib/crewai/src/crewai/llms/providers/snowflake/completion.py
@@ -133,6 +133,9 @@ class SnowflakeCompletion(OpenAICompletion):
     def _format_messages(self, messages: str | list[LLMMessage]) -> list[LLMMessage]:
         formatted_messages = super()._format_messages(messages)
         if self._is_claude_model():
+            formatted_messages = self._remove_incomplete_claude_tool_uses(
+                formatted_messages
+            )
             return self._ensure_claude_conversation_ends_with_user(formatted_messages)
         return formatted_messages
 
@@ -140,6 +143,59 @@ class SnowflakeCompletion(OpenAICompletion):
         model = self.model.lower()
         return model.startswith(("claude-", "anthropic."))
 
+    @staticmethod
+    def _remove_incomplete_claude_tool_uses(
+        messages: list[LLMMessage],
+    ) -> list[LLMMessage]:
+        """Drop dangling Claude tool-use turns before sending to Snowflake.
+
+        Snowflake-hosted Claude models reject histories where an assistant tool
+        use is not accompanied by matching tool results. CrewAI may retry or
+        summarize after an interrupted tool cycle, leaving an assistant
+        ``tool_calls`` message in history without every corresponding
+        ``role='tool'`` result. OpenAI-family models tolerate that more often,
+        but Claude through Snowflake returns:
+        "Each 'toolUse' block must be accompanied with a matching 'toolResult' block."
+        """
+        sanitized: list[LLMMessage] = []
+        index = 0
+
+        while index < len(messages):
+            message = messages[index]
+            tool_calls = message.get("tool_calls") or []
+            if message.get("role") != "assistant" or not tool_calls:
+                sanitized.append(message)
+                index += 1
+                continue
+
+            expected_ids = {
+                tool_call.get("id")
+                for tool_call in tool_calls
+                if isinstance(tool_call, dict) and tool_call.get("id")
+            }
+            if not expected_ids:
+                sanitized.append(message)
+                index += 1
+                continue
+
+            tool_result_ids: set[str] = set()
+            lookahead = index + 1
+            while (
+                lookahead < len(messages) and messages[lookahead].get("role") == "tool"
+            ):
+                tool_call_id = messages[lookahead].get("tool_call_id")
+                if isinstance(tool_call_id, str):
+                    tool_result_ids.add(tool_call_id)
+                lookahead += 1
+
+            if expected_ids.issubset(tool_result_ids):
+                sanitized.append(message)
+                sanitized.extend(messages[index + 1 : lookahead])
+
+            index = lookahead
+
+        return sanitized
+
     @staticmethod
     def _ensure_claude_conversation_ends_with_user(
         messages: list[LLMMessage],
diff --git a/lib/crewai/tests/llms/snowflake/test_snowflake.py b/lib/crewai/tests/llms/snowflake/test_snowflake.py
index 2cc45cdaa..56fc9347a 100644
--- a/lib/crewai/tests/llms/snowflake/test_snowflake.py
+++ b/lib/crewai/tests/llms/snowflake/test_snowflake.py
@@ -156,7 +156,7 @@ class TestSnowflakeRequests:
 
         assert messages == [{"role": "user", "content": "Write a summary."}]
 
-    def test_claude_model_adds_user_turn_after_tool_call_assistant_message(
+    def test_claude_model_removes_dangling_tool_call_without_result(
         self, monkeypatch: pytest.MonkeyPatch
     ):
         _snowflake_env(monkeypatch)
@@ -179,8 +179,43 @@ class TestSnowflakeRequests:
             ]
         )
 
-        assert messages[-2]["role"] == "assistant"
-        assert messages[-2]["tool_calls"][0]["id"] == "call_1"
+        assert messages == [{"role": "user", "content": "Use the tool."}]
+
+    def test_claude_model_preserves_complete_tool_call_result_pair(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        _snowflake_env(monkeypatch)
+        llm = SnowflakeCompletion(model="claude-sonnet-4-5")
+
+        messages = llm._format_messages(
+            [
+                {"role": "user", "content": "Use the tool."},
+                {
+                    "role": "assistant",
+                    "content": None,
+                    "tool_calls": [
+                        {
+                            "id": "call_1",
+                            "type": "function",
+                            "function": {"name": "lookup", "arguments": "{}"},
+                        }
+                    ],
+                },
+                {
+                    "role": "tool",
+                    "tool_call_id": "call_1",
+                    "content": "result",
+                },
+            ]
+        )
+
+        assert messages[-3]["role"] == "assistant"
+        assert messages[-3]["tool_calls"][0]["id"] == "call_1"
+        assert messages[-2] == {
+            "role": "tool",
+            "tool_call_id": "call_1",
+            "content": "result",
+        }
         assert messages[-1]["role"] == "user"
 
     def test_claude_model_maps_max_tokens_to_max_completion_tokens(