docs: align custom_tool document headers (#13252)

On the [Defining Custom
Tools](https://python.langchain.com/docs/modules/agents/tools/custom_tools)
page, there's a 'Subclassing the BaseTool class' paragraph under the
'Completely New Tools - String Input and Output' header. Also there's
another 'Subclassing the BaseTool' paragraph under no header, which I
think may belong to the 'Custom Structured Tools' header.

Another thing is, there's a 'Using the tool decorator' and a 'Using the
decorator' paragraph, I think should belong to 'Completely New Tools -
String Input and Output' and 'Custom Structured Tools' separately.

This PR moves those paragraphs to corresponding headers.

docs/docs/modules/agents/tools/custom_tools.ipynb

@@ -29,7 +29,8 @@
    "outputs": [],
    "source": [
     "# Import things that are needed generically\n",
-    "from langchain.chains import LLMMathChain\nfrom langchain.utilities import SerpAPIWrapper\n",
+    "from langchain.chains import LLMMathChain\n",
+    "from langchain.utilities import SerpAPIWrapper\n",
     "from langchain.agents import AgentType, initialize_agent\n",
     "from langchain.chat_models import ChatOpenAI\n",
     "from langchain.tools import BaseTool, StructuredTool, Tool, tool"
@@ -230,7 +231,7 @@
    "id": "6f12eaf0",
    "metadata": {},
    "source": [
-    "### Subclassing the BaseTool class\n",
+    "### Subclassing the BaseTool\n",
     "\n",
     "You can also directly subclass `BaseTool`. This is useful if you want more control over the instance variables or if you want to propagate callbacks to nested chains or other tools."
    ]
@@ -367,7 +368,7 @@
    "id": "824eaf74",
    "metadata": {},
    "source": [
-    "## Using the `tool` decorator\n",
+    "### Using the decorator\n",
     "\n",
     "To make it easier to define custom tools, a `@tool` decorator is provided. This decorator can be used to quickly create a `Tool` from a simple function. The decorator uses the function name as the tool name by default, but this can be overridden by passing a string as the first argument. Additionally, the decorator will use the function's docstring as the tool's description."
    ]
@@ -531,7 +532,7 @@
    "id": "fb0a38eb",
    "metadata": {},
    "source": [
-    "## Subclassing the BaseTool\n",
+    "### Subclassing the BaseTool\n",
     "\n",
     "The BaseTool automatically infers the schema from the `_run` method's signature."
    ]
@@ -624,7 +625,7 @@
    "id": "7d68b0ac",
    "metadata": {},
    "source": [
-    "## Using the decorator\n",
+    "### Using the decorator\n",
     "\n",
     "The `tool` decorator creates a structured tool automatically if the signature has multiple arguments."
    ]
@@ -774,7 +775,8 @@
     "from langchain.agents import initialize_agent, Tool\n",
     "from langchain.agents import AgentType\n",
     "from langchain.llms import OpenAI\n",
-    "from langchain.chains import LLMMathChain\nfrom langchain.utilities import SerpAPIWrapper\n",
+    "from langchain.chains import LLMMathChain\n",
+    "from langchain.utilities import SerpAPIWrapper\n",
     "\n",
     "search = SerpAPIWrapper()\n",
     "tools = [\n",