diff --git a/llama_stack/providers/inline/tool_runtime/rag/memory.py b/llama_stack/providers/inline/tool_runtime/rag/memory.py
index df0257718..968f93354 100644
--- a/llama_stack/providers/inline/tool_runtime/rag/memory.py
+++ b/llama_stack/providers/inline/tool_runtime/rag/memory.py
@@ -105,7 +105,9 @@ class MemoryToolRuntimeImpl(ToolsProtocolPrivate, ToolRuntime, RAGToolRuntime):
         query_config: RAGQueryConfig | None = None,
     ) -> RAGQueryResult:
         if not vector_db_ids:
-            return RAGQueryResult(content=None)
+            raise ValueError(
+                "No vector DBs were provided to the knowledge search tool. Please provide at least one vector DB ID."
+            )
 
         query_config = query_config or RAGQueryConfig()
         query = await generate_rag_query(
diff --git a/tests/unit/rag/test_rag_query.py b/tests/unit/rag/test_rag_query.py
new file mode 100644
index 000000000..b9fd8cca4
--- /dev/null
+++ b/tests/unit/rag/test_rag_query.py
@@ -0,0 +1,19 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from unittest.mock import MagicMock
+
+import pytest
+
+from llama_stack.providers.inline.tool_runtime.rag.memory import MemoryToolRuntimeImpl
+
+
+class TestRagQuery:
+    @pytest.mark.asyncio
+    async def test_query_raises_on_empty_vector_db_ids(self):
+        rag_tool = MemoryToolRuntimeImpl(config=MagicMock(), vector_io_api=MagicMock(), inference_api=MagicMock())
+        with pytest.raises(ValueError):
+            await rag_tool.query(content=MagicMock(), vector_db_ids=[])