Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.langchain.com/llms.txt

Use this file to discover all available pages before exploring further.

Tools extend what agents can do—letting them fetch real-time data, execute code, query external databases, and take actions in the world. Under the hood, tools are callable functions with well-defined inputs and outputs that get passed to a chat model. The model decides when to invoke a tool based on the conversation context, and what input arguments to provide.
For details on how models handle tool calls, see Tool calling. Trace tool calls and debug errors with LangSmith—follow the tracing quickstart to get set up.

​
Create tools

​
Basic tool definition

The simplest way to create a tool is with the @tool decorator. By default, the function’s docstring becomes the tool’s description that helps the model understand when to use it: 
from langchain.tools import tool

@tool
def search_database(query: str, limit: int = 10) -> str:
    """Search the customer database for records matching the query.

    Args:
        query: Search terms to look for
        limit: Maximum number of results to return
    """
    return f"Found {limit} results for '{query}'"
Type hints are required as they define the tool’s input schema. The docstring should be informative and concise to help the model understand the tool’s purpose.
Server-side tool use: Some chat models feature built-in tools (web search, code interpreters) that are executed server-side. See Server-side tool use for details.
Prefer snake_case for tool names (e.g., web_search instead of Web Search). Some model providers have issues with or reject names containing spaces or special characters with errors. Sticking to alphanumeric characters, underscores, and hyphens helps to improve compatibility across providers.

​
Customize tool properties

​
Custom tool name

By default, the tool name comes from the function name. Override it when you need something more descriptive: 
@tool("web_search")  # Custom name
def search(query: str) -> str:
    """Search the web for information."""
    return f"Results for: {query}"

print(search.name)  # web_search

​
Custom tool description

Override the auto-generated tool description for clearer model guidance: 
@tool("calculator", description="Performs arithmetic calculations. Use this for any math problems.")
def calc(expression: str) -> str:
    """Evaluate mathematical expressions."""
    return str(eval(expression))

​
Advanced schema definition

Define complex inputs with Pydantic models or JSON schemas: 
from pydantic import BaseModel, Field
from typing import Literal

class WeatherInput(BaseModel):
    """Input for weather queries."""
    location: str = Field(description="City name or coordinates")
    units: Literal["celsius", "fahrenheit"] = Field(
        default="celsius",
        description="Temperature unit preference"
    )
    include_forecast: bool = Field(
        default=False,
        description="Include 5-day forecast"
    )

@tool(args_schema=WeatherInput)
def get_weather(location: str, units: str = "celsius", include_forecast: bool = False) -> str:
    """Get current weather and optional forecast."""
    temp = 22 if units == "celsius" else 72
    result = f"Current weather in {location}: {temp} degrees {units[0].upper()}"
    if include_forecast:
        result += "\nNext 5 days: Sunny"
    return result

​
Reserved argument names

The following parameter names are reserved and cannot be used as tool arguments. Using these names will cause runtime errors.
Parameter namePurpose
configReserved for passing RunnableConfig to tools internally
runtimeReserved for ToolRuntime parameter (accessing state, context, store)
To access runtime information, use the ToolRuntime parameter instead of naming your own arguments config or runtime.

​
Access context

Tools are most powerful when they can access runtime information like conversation history, user data, and persistent memory. This section covers how to access and update this information from within your tools. Tools can access runtime information through the ToolRuntime parameter, which provides:
ComponentDescriptionUse case
StateShort-term memory - mutable data that exists for the current conversation (messages, counters, custom fields)Access conversation history, track tool call counts
ContextImmutable configuration passed at invocation time (user IDs, session info)Personalize responses based on user identity
StoreLong-term memory - persistent data that survives across conversationsSave user preferences, maintain knowledge base
Stream WriterEmit real-time updates during tool executionShow progress for long-running operations
Execution InfoIdentity and retry information for the current execution (thread ID, run ID, attempt number)Access thread/run IDs, adjust behavior based on retry state
Server InfoServer-specific metadata when running on LangGraph Server (assistant ID, graph ID, authenticated user)Access assistant ID, graph ID, or authenticated user info
ConfigRunnableConfig for the executionAccess callbacks, tags, and metadata
Tool Call IDUnique identifier for the current tool invocationCorrelate tool calls for logs and model invocations

​
Short-term memory (State)

State represents short-term memory that exists for the duration of a conversation. It includes the message history and any custom fields you define in your graph state.
Add runtime: ToolRuntime to your tool signature to access state. This parameter is automatically injected and hidden from the LLM - it won’t appear in the tool’s schema.

​
Access state

Tools can access the current conversation state using runtime.state: 
from langchain.tools import tool, ToolRuntime
from langchain.messages import HumanMessage

@tool
def get_last_user_message(runtime: ToolRuntime) -> str:
    """Get the most recent message from the user."""
    messages = runtime.state["messages"]

    # Find the last human message
    for message in reversed(messages):
        if isinstance(message, HumanMessage):
            return message.content

    return "No user messages found"

# Access custom state fields
@tool
def get_user_preference(
    pref_name: str,
    runtime: ToolRuntime
) -> str:
    """Get a user preference value."""
    preferences = runtime.state.get("user_preferences", {})
    return preferences.get(pref_name, "Not set")
The runtime parameter is hidden from the model. For the example above, the model only sees pref_name in the tool schema.

​
Update state

Use Command to update the agent’s state. This is useful for tools that need to update custom state fields. Include a ToolMessage in the update so the model can see the result of the tool call: 
from langchain.agents import AgentState
from langchain.messages import ToolMessage
from langchain.tools import ToolRuntime, tool
from langgraph.types import Command


class CustomState(AgentState):
    user_name: str


@tool
def set_user_name(new_name: str, runtime: ToolRuntime[None, CustomState]) -> Command:
    """Set the user's name in the conversation state."""
    return Command(
        update={
            "user_name": new_name,
            "messages": [
                ToolMessage(
                    content=f"User name set to {new_name}.",
                    tool_call_id=runtime.tool_call_id,
                )
            ],
        }
    )
When tools update state variables, consider defining a reducer for those fields. Since LLMs can call multiple tools in parallel, a reducer determines how to resolve conflicts when the same state field is updated by concurrent tool calls.

​
Context

Context provides immutable configuration data that is passed at invocation time. Use it for user IDs, session details, or application-specific settings that shouldn’t change during a conversation. Access context through runtime.context: 
from dataclasses import dataclass
from langchain_openai import ChatOpenAI
from langchain.agents import create_agent
from langchain.tools import tool, ToolRuntime


USER_DATABASE = {
    "user123": {
        "name": "Alice Johnson",
        "account_type": "Premium",
        "balance": 5000,
        "email": "alice@example.com"
    },
    "user456": {
        "name": "Bob Smith",
        "account_type": "Standard",
        "balance": 1200,
        "email": "bob@example.com"
    }
}

@dataclass
class UserContext:
    user_id: str

@tool
def get_account_info(runtime: ToolRuntime[UserContext]) -> str:
    """Get the current user's account information."""
    user_id = runtime.context.user_id

    if user_id in USER_DATABASE:
        user = USER_DATABASE[user_id]
        return f"Account holder: {user['name']}\nType: {user['account_type']}\nBalance: ${user['balance']}"
    return "User not found"

model = ChatOpenAI(model="gpt-5.4")
agent = create_agent(
    model,
    tools=[get_account_info],
    context_schema=UserContext,
    system_prompt="You are a financial assistant."
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What's my current balance?"}]},
    context=UserContext(user_id="user123")
)

​
Long-term memory (Store)

The BaseStore provides persistent storage that survives across conversations. Unlike state (short-term memory), data saved to the store remains available in future sessions. Access the store through runtime.store. The store uses a namespace/key pattern to organize data:
For production deployments, use a persistent store implementation like PostgresStore instead of InMemoryStore. See the memory documentation for setup details.
from typing import Any
from langgraph.store.memory import InMemoryStore
from langchain.agents import create_agent
from langchain.tools import tool, ToolRuntime
from langchain_openai import ChatOpenAI

# Access memory
@tool
def get_user_info(user_id: str, runtime: ToolRuntime) -> str:
    """Look up user info."""
    store = runtime.store
    user_info = store.get(("users",), user_id)
    return str(user_info.value) if user_info else "Unknown user"

# Update memory
@tool
def save_user_info(user_id: str, user_info: dict[str, Any], runtime: ToolRuntime) -> str:
    """Save user info."""
    store = runtime.store
    store.put(("users",), user_id, user_info)
    return "Successfully saved user info."

model = ChatOpenAI(model="gpt-5.4")

store = InMemoryStore()
agent = create_agent(
    model,
    tools=[get_user_info, save_user_info],
    store=store
)

# First session: save user info
agent.invoke({
    "messages": [{"role": "user", "content": "Save the following user: userid: abc123, name: Foo, age: 25, email: foo@langchain.dev"}]
})

# Second session: get user info
agent.invoke({
    "messages": [{"role": "user", "content": "Get user info for user with id 'abc123'"}]
})
# Here is the user info for user with ID "abc123":
# - Name: Foo
# - Age: 25
# - Email: foo@langchain.dev

​
Stream writer

Stream real-time updates from tools during execution. This is useful for providing progress feedback to users during long-running operations. Use runtime.stream_writer to emit custom updates: 
from langchain.tools import tool, ToolRuntime

@tool
def get_weather(city: str, runtime: ToolRuntime) -> str:
    """Get weather for a given city."""
    writer = runtime.stream_writer

    # Stream custom updates as the tool executes
    writer(f"Looking up data for city: {city}")
    writer(f"Acquired data for city: {city}")

    return f"It's always sunny in {city}!"
If you use runtime.stream_writer inside your tool, the tool must be invoked within a LangGraph execution context. See Streaming for more details.

​
Execution info

Access thread ID, run ID, and retry state from within a tool via runtime.execution_info: 
from langchain.tools import tool, ToolRuntime

@tool
def log_execution_context(runtime: ToolRuntime) -> str:
    """Log execution identity information."""
    info = runtime.execution_info
    print(f"Thread: {info.thread_id}, Run: {info.run_id}")
    print(f"Attempt: {info.node_attempt}")
    return "done"
Requires deepagents>=0.5.0 (or langgraph>=1.1.5).

​
Server info

When your tool runs on LangGraph Server, access the assistant ID, graph ID, and authenticated user via runtime.server_info: 
from langchain.tools import tool, ToolRuntime

@tool
def get_assistant_scoped_data(runtime: ToolRuntime) -> str:
    """Fetch data scoped to the current assistant."""
    server = runtime.server_info
    if server is not None:
        print(f"Assistant: {server.assistant_id}, Graph: {server.graph_id}")
        if server.user is not None:
            print(f"User: {server.user.identity}")
    return "done"
server_info is None when the tool is not running on LangGraph Server (e.g., during local development or testing).
Requires deepagents>=0.5.0 (or langgraph>=1.1.5).

​
Tool execution

In LangChain, tools are used by agents (for example via create_agent) and tool error handling is configured through middleware. For LangGraph workflows, tool execution is handled by ToolNode. See ToolNode.

​
Tool return values

You can choose different return values for your tools:
  • Return a string for human-readable results.
  • Return an object for structured results the model should parse.
  • Return a Command with optional message when you need to write to state.

​
Return a string

Return a string when the tool should provide plain text for the model to read and use in its next response. 
from langchain.tools import tool


@tool
def get_weather(city: str) -> str:
    """Get weather for a city."""
    return f"It is currently sunny in {city}."
Behavior:
  • The return value is converted to a ToolMessage.
  • The model sees that text and decides what to do next.
  • No agent state fields are changed unless the model or another tool does so later.
Use this when the result is naturally human-readable text.

​
Return an object

Return an object (for example, a dict) when your tool produces structured data that the model should inspect. 
from langchain.tools import tool


@tool
def get_weather_data(city: str) -> dict:
    """Get structured weather data for a city."""
    return {
        "city": city,
        "temperature_c": 22,
        "conditions": "sunny",
    }
Behavior:
  • The object is serialized and sent back as tool output.
  • The model can read specific fields and reason over them.
  • Like string returns, this does not directly update graph state.
Use this when downstream reasoning benefits from explicit fields instead of free-form text.

​
Return a Command

Return a Command when the tool needs to update graph state (for example, setting user preferences or app state). You can return a Command with or without including a ToolMessage. If the model needs to see that the tool succeeded (for example, to confirm a preference change), include a ToolMessage in the update, using runtime.tool_call_id for the tool_call_id parameter. 
from langchain.messages import ToolMessage
from langchain.tools import ToolRuntime, tool
from langgraph.types import Command


@tool
def set_language(language: str, runtime: ToolRuntime) -> Command:
    """Set the preferred response language."""
    return Command(
        update={
            "preferred_language": language,
            "messages": [
                ToolMessage(
                    content=f"Language set to {language}.",
                    tool_call_id=runtime.tool_call_id,
                )
            ],
        }
    )
Behavior:
  • The command updates state using update.
  • Updated state is available to subsequent steps in the same run.
  • Use reducers for fields that may be updated by parallel tool calls.
Use this when the tool is not just returning data, but also mutating agent state.

​
Error handling

Handle tool errors using LangChain agent middleware to retry failed tool calls or return custom error messages: 
from collections.abc import Callable

from langchain.agents import create_agent
from langchain.agents.middleware import wrap_tool_call
from langchain.messages import ToolMessage
from langchain.tools.tool_node import ToolCallRequest


@wrap_tool_call
def handle_tool_errors(
    request: ToolCallRequest,
    handler: Callable[[ToolCallRequest], ToolMessage],
) -> ToolMessage:
    """Convert tool exceptions into ToolMessages the model can handle."""
    try:
        return handler(request)
    except Exception as e:
        return ToolMessage(
            content=f"Tool error: Please check your input and try again. ({e})",
            tool_call_id=request.tool_call["id"],
        )


agent = create_agent(
    model="google_genai:gemini-3.1-pro-preview",
    tools=[],
    middleware=[handle_tool_errors],
)

​
State injection

Tools can access the current graph state through ToolRuntime: 
from langchain.tools import tool, ToolRuntime

@tool
def get_message_count(runtime: ToolRuntime) -> str:
    """Get the number of messages in the conversation."""
    messages = runtime.state["messages"]
    return f"There are {len(messages)} messages."
For more details on accessing state, context, and long-term memory from tools, see Access context.

​
Prebuilt tools

LangChain provides a large collection of prebuilt tools and toolkits for common tasks like web search, code interpretation, database access, and more. These ready-to-use tools can be directly integrated into your agents without writing custom code. See the tools and toolkits integration page for a complete list of available tools organized by category.

​
Server-side tool use

Some chat models feature built-in tools that are executed server-side by the model provider. These include capabilities like web search and code interpreters that don’t require you to define or host the tool logic. Refer to the individual chat model integration pages and the tool calling documentation for details on enabling and using these built-in tools.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.
Edit this page on GitHub or file an issue.