address review comments

Author: bilgeyucel

notebooks/agent_powered_retrieval.ipynb

@@ -657,7 +657,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 21,
+      "execution_count": null,
       "metadata": {
         "id": "ptPCVVRKghQY"
       },
@@ -668,7 +668,7 @@
         "def retrieval_function(\n",
         "    query: Optional[str] = None,\n",
         "    metadata_filters: Optional[Dict[str, Any]] = None,\n",
-        "    top_k: Optional[int] = 5\n",
+        "    top_k: int = 5\n",
         ") -> List[Document]:\n",
         "\n",
         "    retrieved_documents = []\n",
@@ -685,8 +685,7 @@
         "    # If there's only `metadata_filters`\n",
         "    else:\n",
         "        retrieved_documents = filter_retriever.run(filters=metadata_filters)\n",
-        "        if len(retrieved_documents.get(\"documents\")) > top_k:\n",
-        "            retrieved_documents[\"documents\"] = retrieved_documents[\"documents\"][:top_k]\n",
+        "        retrieved_documents[\"documents\"] = retrieved_documents[\"documents\"][:top_k]\n",
         "\n",
         "    return retrieved_documents"
       ]
@@ -697,7 +696,9 @@
         "id": "bcCbVu9PDWTG"
       },
       "source": [
-        "Define the JSON schema for tool parameters, including `query`, `top_k`, and `metadata_filters`, to validate and structure tool calls."
+        "Define the JSON schema for your tool parameters, such as `query`, `top_k`, and `metadata_filters`, to ensure tool calls are properly structured and validated.\n",
+        "\n",
+        "> In most cases, you don’t need to define `parameters` manually. When you use the [@tool decorator](https://docs.haystack.deepset.ai/docs/tool#tool-decorator) or [create_tool_from_function](https://docs.haystack.deepset.ai/docs/tool#create_tool_from_function), Haystack automatically infers the tool’s name, description, and parameters from the function and generates a matching JSON schema for you."
       ]
     },
     {