diff --git a/litellm/llms/anthropic/pass_through/responses_adapters/transformation.py b/litellm/llms/anthropic/pass_through/responses_adapters/transformation.py
index 26f82d66bfc..d7c6bb658ba 100644
--- a/litellm/llms/anthropic/pass_through/responses_adapters/transformation.py
+++ b/litellm/llms/anthropic/pass_through/responses_adapters/transformation.py
@@ -305,9 +305,13 @@ class LiteLLMAnthropicToResponsesAPIAdapter:
                             elif isinstance(inner, str):
                                 output_text = inner
                             elif isinstance(inner, list):
-                                parts = [
-                                    c.get("text", "") for c in inner if isinstance(c, dict) and c.get("type") == "text"
-                                ]
+                                parts = (
+                                    c.get("text", "")
+                                    if c.get("type") == "text"
+                                    else f"[Loaded tool: {c.get('tool_name', '')}]"
+                                    for c in inner
+                                    if isinstance(c, dict) and c.get("type") in {"text", "tool_reference"}
+                                )
                                 output_text = "\n".join(parts)
                                 image_candidates = tuple(
                                     self._translate_anthropic_image_source_to_url(c.get("source"))
diff --git a/tests/unit/llms/anthropic/pass_through/responses_adapters/test_responses_adapters_transformation.py b/tests/unit/llms/anthropic/pass_through/responses_adapters/test_responses_adapters_transformation.py
index 9b6b44c3d05..97f8512e55f 100644
--- a/tests/unit/llms/anthropic/pass_through/responses_adapters/test_responses_adapters_transformation.py
+++ b/tests/unit/llms/anthropic/pass_through/responses_adapters/test_responses_adapters_transformation.py
@@ -481,6 +481,33 @@ class TestTranslateMessagesToResponsesInput:
         result = _translate_messages(messages)
         assert result[0]["output"] == "Line 1\nLine 2"
 
+    def test_user_tool_result_list_content_preserves_tool_references(self):
+        messages = [
+            {
+                "role": "user",
+                "content": [
+                    {
+                        "type": "tool_result",
+                        "tool_use_id": "call_search",
+                        "content": [
+                            {"type": "text", "text": "Available:"},
+                            {"type": "tool_reference", "tool_name": "get_weather"},
+                        ],
+                    }
+                ],
+            }
+        ]
+
+        result = _translate_messages(messages)
+
+        assert result == [
+            {
+                "type": "function_call_output",
+                "call_id": "call_search",
+                "output": "Available:\n[Loaded tool: get_weather]",
+            }
+        ]
+
     def test_user_tool_result_null_content(self):
         """tool_result with null content becomes empty string output."""
         messages = [