docs(agents): tools page (#4287)

Co-authored-by: Vadym Barda <vadym@langchain.dev>

Author: eyurtsev

docs/docs/agents/tools.md

@@ -2,7 +2,9 @@
 
 [Tools](https://python.langchain.com/docs/concepts/tools/) are a way to encapsulate a function and its input schema in a way that can be passed to a chat model that supports tool calling. This allows the model to request the execution of this function with specific inputs.
 
-## Create tools
+You can either [define your own tools](#define-simple-tools) or use [prebuilt integrations](#prebuilt-tools) that LangChain provides.
+
+## Define simple tools
 
 You can pass a vanilla function to `create_react_agent` to use as a tool:
 
@@ -21,7 +23,7 @@ create_react_agent(
 
 ## Customize tools
 
-If you want more control over how the tool is created, you can use `@tool` decorator:
+For more control over tool behavior, use the `@tool` decorator:
 
 ```python
 # highlight-next-line
@@ -39,7 +41,7 @@ def multiply(a: int, b: int) -> int:
     return a * b
 ```
 
-A common pattern is defining a custom tool input schema as a Pydantic model:
+You can also define a custom input schema using Pydantic:
 
 ```python
 from pydantic import BaseModel, Field
@@ -55,11 +57,14 @@ def multiply(a: int, b: int) -> int:
    return a * b
 ```
 
-For even more control and creating custom LangChain tools, see [this guide](https://python.langchain.com/docs/how_to/custom_tools/).
+For additional customization, refer to the [custom tools guide](https://python.langchain.com/docs/how_to/custom_tools/).
 
 ## Hide arguments from the model
 
-There are cases where certain arguments need to be passed to a tool at runtime but should not be generated by the model itself. In LangGraph's `create_react_agent`, you might want to pass agent [state](./context.md#via-state-tools) or [config](./context.md#via-config-tools) to the tools.
+Some tools require runtime-only arguments (e.g., user ID or session context) that should not be controllable by the model.
+
+You can put these arguments in the `state` or `config` of the agent, and access
+this information inside the tool:
 
 ```python
 from langgraph.prebuilt import InjectedState
@@ -82,9 +87,12 @@ def my_tool(
     ...
 ```
 
-## Parallel tool calling
+## Disable parallel tool calling
+
+Some model providers support executing multiple tools in parallel, but
+allow users to disable this feature.
 
-Some model providers allow their models to request execution of several tools at once and allow users to explicitly enable or disable parallel tool calling. You can control this in `create_react_agent` via passing a `ChatModel` instance with bound tools:
+For supported providers, you can disable parallel tool calling by setting `parallel_tool_calls=False` via the `model.bind_tools()` method:
 
 ```python
 from langchain.chat_models import init_chat_model
@@ -111,7 +119,7 @@ agent.invoke({"messages": "what's 3 + 5 and 4 * 7? make both calculations in par
 
 ## Return tool results directly
 
-`create_react_agent` allows you to return tool response directly and end the tool-calling loop early. To do so, you must specify `return_direct=True` when creating your tool:
+Use `return_direct=True` to return tool results immediately and stop the agent loop:
 
 ```python
 from langchain_core.tools import tool
@@ -132,14 +140,7 @@ agent.invoke({"messages": "what's 3 + 5?"})
 
 ## Force tool use
 
-Similar to parallel tool calling, certain providers allow users to specify `tool_choice`, indicating if the agent is always required to call a certain tools (or any tool). You can similarly control this via `model.bind_tools()`.
-
-!!! Warning
-
-    If you set `tool_choice` to always call a particular tool, you will end up with an infinite tool-calling loop, as the stopping condition for `create_react_agent` is the absence of tool calls requested by an LLM. To address this you have a few options:
-
-    - mark your tool as `return_direct=True`. This will stop the agent loop after the the tool is executed for the first time (used in example below). 
-    - specify `recursion_limit` when invoking the agent. This will limit the maximum number of graph steps that the agent can take before hitting an GraphRecursionError.
+To force the agent to use specific tools, you can set the `tool_choice` option in `model.bind_tools()`:
 
 ```python
 from langchain_core.tools import tool
@@ -159,4 +160,28 @@ agent = create_react_agent(
 )
 
 agent.invoke({"messages": "Hi, I am Bob"})
-```
+```
+
+!!! Warning "Avoid infinite loops"
+
+    Forcing tool usage without stopping conditions can create infinite loops. Use one of the following safeguards:
+
+    - Mark the tool with [`return_direct=True`](#return-tool-results-directly) to end the loop after execution.
+    - Set [`recursion_limit`](../concepts/low_level.md#recursion-limit) to restrict the number of execution steps.
+
+## Prebuilt tools
+
+LangChain supports a wide range of prebuilt tool integrations for interacting with APIs, databases, file systems, web data, and more. These tools extend the functionality of agents and enable rapid development.
+
+You can browse the full list of available integrations in the [LangChain integrations directory](https://python.langchain.com/docs/integrations/tools/).
+
+Some commonly used tool categories include:
+
+- **Search**: Bing, SerpAPI, Tavily
+- **Code interpreters**: Python REPL, Node.js REPL
+- **Databases**: SQL, MongoDB, Redis
+- **Web data**: Web scraping and browsing
+- **APIs**: OpenWeatherMap, NewsAPI, and others
+
+These integrations can be configured and added to your agents using the same `tools` parameter shown in the examples above.
+