Skip to content

Create custom tools

Turn a function you write into a tool the agent can call. Strands gives you a few ways to define one, and the Python and TypeScript forms differ slightly.

Python supports three approaches to defining tools:

  • Python functions with the @tool decorator: Turn a regular function into a tool by adding a decorator. The decorator uses the function’s docstring and type hints to generate the tool specification.

  • Class-based tools with the @tool decorator: Create tools within classes to maintain state and use object-oriented patterns.

  • Python modules following a specific format: Define tools by creating Python modules that contain a tool specification and a matching function. This approach gives you more control over the tool’s definition and is useful for dependency-free implementations of tools.

Tool Creation Examples

Section titled “Tool Creation Examples”

Basic Example

Section titled “Basic Example”

Here’s a simple example of a function decorated as a tool:

from strands import tool


@tool
def weather_forecast(city: str, days: int = 3) -> str:
    """Get weather forecast for a city.


    Args:
        city: The name of the city
        days: Number of days for the forecast
    """
    return f"Weather forecast for {city} for the next {days} days..."

The decorator extracts information from your function’s docstring to create the tool specification. The first paragraph becomes the tool’s description, and the “Args” section provides parameter descriptions. These are combined with the function’s type hints to create a complete tool specification.

Overriding Tool Name, Description, and Schema

Section titled “Overriding Tool Name, Description, and Schema”

Override the tool name, description, and input schema by passing them to the decorator:

@tool(name="get_weather", description="Retrieves weather forecast for a specified location")
def weather_forecast(city: str, days: int = 3) -> str:
    """Implementation function for weather forecasting.


    Args:
        city: The name of the city
        days: Number of days for the forecast
    """
    return f"Weather forecast for {city} for the next {days} days..."

Tool names must match ^[a-zA-Z0-9_-]+$ and be 1 to 64 characters long. Names that do not match this format are replaced with INVALID_TOOL_NAME on assistant messages before they are sent to the model, so the request still succeeds but the model can no longer reference the original name.

Overriding Input Schema

Section titled “Overriding Input Schema”

Provide a custom JSON schema to override the automatically generated one:

@tool(
    inputSchema={
        "json": {
            "type": "object",
            "properties": {
                "shape": {
                    "type": "string",
                    "enum": ["circle", "rectangle"],
                    "description": "The shape type"
                },
                "radius": {"type": "number", "description": "Radius for circle"},
                "width": {"type": "number", "description": "Width for rectangle"},
                "height": {"type": "number", "description": "Height for rectangle"}
            },
            "required": ["shape"]
        }
    }
)
def calculate_area(shape: str, radius: float = None, width: float = None, height: float = None) -> float:
    """Calculate area of a shape."""
    if shape == "circle":
        return 3.14159 * radius ** 2
    elif shape == "rectangle":
        return width * height
    return 0.0

Using and Customizing Tools

Section titled “Using and Customizing Tools”

Loading Function-Based Tools

Section titled “Loading Function-Based Tools”

To use function-based tools, pass them to the agent:

agent = Agent(
    tools=[weather_forecast]
)

Custom Return Type

Section titled “Custom Return Type”

By default, your function’s return value is formatted as a text response. To control the response format, return a dictionary with the tool result structure:

@tool
def fetch_data(source_id: str) -> dict:
    """Fetch data from a specified source.


    Args:
        source_id: Identifier for the data source
    """
    try:
        data = some_other_function(source_id)
        return {
            "status": "success",
            "content": [ {
                "json": data,
            }]
        }
    except Exception as e:
        return {
            "status": "error",
             "content": [
                {"text": f"Error:{e}"}
            ]
        }

For the full structure, see Tool result format.

Async Invocation

Section titled “Async Invocation”

Function tools can also be async. Strands invokes all async tools concurrently.

import asyncio
from strands import Agent, tool




@tool
async def call_api() -> str:
    """Call API asynchronously."""


    await asyncio.sleep(5)  # simulated api call
    return "API result"




async def async_example():
    agent = Agent(tools=[call_api])
    await agent.invoke_async("Can you call my API?")




asyncio.run(async_example())

ToolContext

Section titled “ToolContext”

Tools can access their execution context to interact with the invoking agent, current tool use data, and invocation state. The ToolContext provides this access:

Set context=True in the decorator and include a tool_context parameter:

from strands import tool, Agent, ToolContext


@tool(context=True)
def get_self_name(tool_context: ToolContext) -> str:
    return f"The agent name is {tool_context.agent.name}"


@tool(context=True)
def get_tool_use_id(tool_context: ToolContext) -> str:
    return f"Tool use is {tool_context.tool_use["toolUseId"]}"


@tool(context=True)
def get_invocation_state(tool_context: ToolContext) -> str:
    return f"Invocation state: {tool_context.invocation_state["custom_data"]}"


agent = Agent(tools=[get_self_name, get_tool_use_id, get_invocation_state], name="Best agent")


agent("What is your name?")
agent("What is the tool use id?")
agent("What is the invocation state?", custom_data="You're the best agent ;)")

Custom ToolContext Parameter Name

Section titled “Custom ToolContext Parameter Name”

To use a different parameter name for ToolContext, pass that name as the value of the context argument:

from strands import tool, Agent, ToolContext


@tool(context="context")
def get_self_name(context: ToolContext) -> str:
    return f"The agent name is {context.agent.name}"


agent = Agent(tools=[get_self_name], name="Best agent")


agent("What is your name?")

Accessing State in Tools

Section titled “Accessing State in Tools”

The invocation_state attribute in ToolContext provides access to data passed through the agent invocation. Use it for:

  1. Request Context: Access session IDs, user information, or request-specific data
  2. Multi-Agent Shared State: In Graph and Swarm patterns, access state shared across all agents
  3. Per-Invocation Overrides: Override behavior or settings for specific requests
from strands import tool, Agent, ToolContext
import requests


@tool(context=True)
def api_call(query: str, tool_context: ToolContext) -> dict:
    """Make an API call with user context.


    Args:
        query: The search query to send to the API
        tool_context: Context containing user information
    """
    user_id = tool_context.invocation_state.get("user_id")


    response = requests.get(
        "https://api.example.com/search",
        headers={"X-User-ID": user_id},
        params={"q": query}
    )


    return response.json()


agent = Agent(tools=[api_call])
result = agent("Get my profile data", user_id="user123")

Invocation State Compared To Other Approaches

Invocation state differs from other approaches that affect tool execution:

  • Tool Parameters: Use for data that the LLM should reason about and provide based on the user’s request. Examples include search queries, file paths, calculation inputs, or any data the agent needs to determine from context.

  • Invocation State: Use for context and configuration that should not appear in prompts but affects tool behavior. Best suited for parameters that can change between agent invocations. Examples include user IDs for personalization, session IDs, or user flags.

  • Class-based tools: Use for configuration that doesn’t change between requests and requires initialization. Examples include API keys, database connection strings, service endpoints, or shared resources that need setup.

Tool Streaming

Section titled “Tool Streaming”

Async tools can yield intermediate results to provide real-time progress updates. Each yielded value becomes a streaming event, with the final value serving as the tool’s return result:

from datetime import datetime
import asyncio
from strands import tool


@tool
async def process_dataset(records: int) -> str:
    """Process records with progress updates."""
    start = datetime.now()


    for i in range(records):
        await asyncio.sleep(0.1)
        if i % 10 == 0:
            elapsed = datetime.now() - start
            yield f"Processed {i}/{records} records in {elapsed.total_seconds():.1f}s"


    yield f"Completed {records} records in {(datetime.now() - start).total_seconds():.1f}s"

Stream events contain a tool_stream_event dictionary with tool_use (invocation info) and data (yielded value) fields:

async def tool_stream_example():
    agent = Agent(tools=[process_dataset])


    async for event in agent.stream_async("Process 50 records"):
        if tool_stream := event.get("tool_stream_event"):
            if update := tool_stream.get("data"):
                print(f"Progress: {update}")


asyncio.run(tool_stream_example())

Class-Based Tools

Section titled “Class-Based Tools”

Class-based tools maintain state and use object-oriented patterns. Reach for them when your tools need to share resources, keep context between invocations, follow object-oriented design, customize a tool before passing it to an agent, or create different tool configurations for different agents.

Example with Multiple Tools in a Class

Section titled “Example with Multiple Tools in a Class”

Define multiple tools in the same class to group related functionality:

from strands import Agent, tool


class DatabaseTools:
    def __init__(self, connection_string):
        self.connection = self._establish_connection(connection_string)


    def _establish_connection(self, connection_string):
        # Set up database connection
        return {"connected": True, "db": "example_db"}


    @tool
    def query_database(self, sql: str) -> dict:
        """Run a SQL query against the database.


        Args:
            sql: The SQL query to execute
        """
        # Uses the shared connection
        return {"results": f"Query results for: {sql}", "connection": self.connection}


    @tool
    def insert_record(self, table: str, data: dict) -> str:
        """Insert a new record into the database.


        Args:
            table: The table name
            data: The data to insert as a dictionary
        """
        # Also uses the shared connection
        return f"Inserted data into {table}: {data}"


# Usage
db_tools = DatabaseTools("example_connection_string")
agent = Agent(
    tools=[db_tools.query_database, db_tools.insert_record]
)

When you use the @tool decorator on a class method, the method becomes bound to the class instance when instantiated. This means the tool function has access to the instance’s attributes and can maintain state between invocations.

Module Based Tools (python only)

Section titled “Module Based Tools (python only)”

An alternative approach is to define a tool as a Python module with a specific structure. This enables creating tools that don’t depend on the SDK directly.

A Python module tool requires two key components:

  1. A TOOL_SPEC variable that defines the tool’s name, description, and input schema
  2. A function with the same name as specified in the tool spec that implements the tool’s functionality

Basic Example

Section titled “Basic Example”

Here’s how you would implement the same weather forecast tool as a module:

weather_forecast.py
from typing import Any




# 1. Tool Specification
TOOL_SPEC = {
    "name": "weather_forecast",
    "description": "Get weather forecast for a city.",
    "inputSchema": {
        "json": {
            "type": "object",
            "properties": {
                "city": {
                    "type": "string",
                    "description": "The name of the city"
                },
                "days": {
                    "type": "integer",
                    "description": "Number of days for the forecast",
                    "default": 3
                }
            },
            "required": ["city"]
        }
    }
}


# 2. Tool Function
def weather_forecast(tool, **kwargs: Any):
    # Extract tool parameters
    tool_use_id = tool["toolUseId"]
    tool_input = tool["input"]


    # Get parameter values
    city = tool_input.get("city", "")
    days = tool_input.get("days", 3)


    # Tool implementation
    result = f"Weather forecast for {city} for the next {days} days..."


    # Return structured response
    return {
        "toolUseId": tool_use_id,
        "status": "success",
        "content": [{"text": result}]
    }

Loading Module Tools

Section titled “Loading Module Tools”

To use a module-based tool, import the module and pass it to the agent:

from strands import Agent
import weather_forecast


agent = Agent(
    tools=[weather_forecast]
)

You can also load a tool by passing a path:

from strands import Agent


agent = Agent(
    tools=["./weather_forecast.py"]
)

Async Invocation

Section titled “Async Invocation”

Like decorated tools, module tools can be async.

TOOL_SPEC = {
    "name": "call_api",
    "description": "Call my API asynchronously.",
    "inputSchema": {
        "json": {
            "type": "object",
            "properties": {},
            "required": []
        }
    }
}


async def call_api(tool, **kwargs):
    await asyncio.sleep(5)  # simulated api call
    result = "API result"


    return {
        "toolUseId": tool["toolUseId"],
        "status": "success",
        "content": [{"text": result}],
    }

Write effective tool descriptions

Section titled “Write effective tool descriptions”

Language models rely heavily on tool descriptions to determine when and how to use them. Well-crafted descriptions significantly improve tool usage accuracy.

A good tool description should:

  • Clearly explain the tool’s purpose and functionality
  • Specify when the tool should be used
  • Detail the parameters it accepts and their formats
  • Describe the expected output format
  • Note any limitations or constraints

Example of a well-described tool:

@tool
def search_database(query: str, max_results: int = 10) -> list:
    """
    Search the product database for items matching the query string.


    Use this tool when you need to find detailed product information based on keywords,
    product names, or categories. The search is case-insensitive and supports fuzzy
    matching to handle typos and variations in search terms.


    This tool connects to the enterprise product catalog database and performs a semantic
    search across all product fields, providing comprehensive results with all available
    product metadata.


    Example response:
        [
            {
                "id": "P12345",
                "name": "Ultra Comfort Running Shoes",
                "description": "Lightweight running shoes with...",
                "price": 89.99,
                "category": ["Footwear", "Athletic", "Running"]
            },
            ...
        ]


    Notes:
        - This tool only searches the product catalog and does not provide
          inventory or availability information
        - Results are cached for 15 minutes to improve performance
        - The search index updates every 6 hours, so very recent products may not appear
        - For real-time inventory status, use a separate inventory check tool


    Args:
        query: The search string (product name, category, or keywords)
               Example: "red running shoes" or "smartphone charger"
        max_results: Maximum number of results to return (default: 10, range: 1-100)
                     Use lower values for faster response when exact matches are expected


    Returns:
        A list of matching product records, each containing:
        - id: Unique product identifier (string)
        - name: Product name (string)
        - description: Detailed product description (string)
        - price: Current price in USD (float)
        - category: Product category hierarchy (list)
    """


    # Implementation
    pass