Custom server tools

When using Letta Code and the Letta Code SDK, the recommended way to extend your agent’s abilities is via skills, not custom server-side tools.

Skills are easier for the agent to configure and maintain, and can be easily modified by the agent itself (e.g. to correct mistakes).

You can create custom tools in Letta using the Python SDK, as well as via the ADE tool builder.

For your agent to call a tool, Letta constructs an OpenAI tool schema (contained in json_schema field) from the function you define. Letta can either parse this automatically from a properly formatting docstring, or you can pass in the schema explicitly by providing a Pydantic object that defines the argument schema.

Creating a custom tool

Custom TypeScript (server) tools work out-of-the-box with the Letta API, but require an E2B_API_KEY for Docker deployments. To have your agent run arbitrary TypeScript code without a sandbox key, use client tools.

Specifying tools via Pydantic models

To create a custom tool, you can extend the BaseTool class and specify the following:

• name - The name of the tool
• args_schema - A Pydantic model that defines the arguments for the tool
• description - A description of the tool
• tags - (Optional) A list of tags for the tool to query You must also define a run(..) method for the tool code that takes in the fields from the args_schema.

Below is an example of how to create a tool by extending BaseTool:

from letta_client import Letta
from letta_client.client import BaseTool
from pydantic import BaseModel
from typing import List, Type
import os

class InventoryItem(BaseModel):
    sku: str  # Unique product identifier
    name: str  # Product name
    price: float  # Current price
    category: str  # Product category (e.g., "Electronics", "Clothing")

class InventoryEntry(BaseModel):
    timestamp: int  # Unix timestamp of the transaction
    item: InventoryItem  # The product being updated
    transaction_id: str  # Unique identifier for this inventory update

class InventoryEntryData(BaseModel):
    data: InventoryEntry
    quantity_change: int  # Change in quantity (positive for additions, negative for removals)


class ManageInventoryTool(BaseTool):
    name: str = "manage_inventory"
    args_schema: Type[BaseModel] = InventoryEntryData
    description: str = "Update inventory catalogue with a new data entry"
    tags: List[str] = ["inventory", "shop"]

    def run(self, data: InventoryEntry, quantity_change: int) -> bool:
        print(f"Updated inventory for {data.item.name} with a quantity change of {quantity_change}")
        return True

# create a client connected to the Letta API
# Get your API key at https://app.letta.com/api-keys
client = Letta(api_key=os.getenv("LETTA_API_KEY"))

# create the tool
tool_from_class = client.tools.add(
    tool=ManageInventoryTool(),
)

To add this tool using the SDK:

from letta_client import Letta

# create a client to connect to your local Letta server
client = Letta(
  base_url="http://localhost:8283"
)

# create the tool
tool_from_class = client.tools.add(
    tool=ManageInventoryTool(),
)

Specifying tools via function docstrings

You can create a tool by passing in a function with a Google Style Python docstring specifying the arguments and description of the tool:

# install letta_client with `pip install letta-client`
from letta_client import Letta
import os

# create a client connected to the Letta API
client = Letta(api_key=os.getenv("LETTA_API_KEY"))

# define a function with a docstring
def roll_dice() -> str:
    """
    Simulate the roll of a 20-sided die (d20).

    This function generates a random integer between 1 and 20, inclusive,
    which represents the outcome of a single roll of a d20.

    Returns:
        str: The result of the die roll.
    """
    import random

    dice_role_outcome = random.randint(1, 20)
    output_string = f"You rolled a {dice_role_outcome}"
    return output_string

# create the tool
tool = client.tools.create_from_function(
    func=roll_dice
)

The tool creation will return a Tool object. You can update the tool with client.tools.upsert_from_function(...).

Specifying arguments via Pydantic models

To specify the arguments for a complex tool, you can use the args_schema parameter.

# install letta_client with `pip install letta-client`
from letta_client import Letta

class Step(BaseModel):
    name: str = Field(
        ...,
        description="Name of the step.",
    )
    description: str = Field(
        ...,
        description="An exhaustic description of what this step is trying to achieve and accomplish.",
    )


class StepsList(BaseModel):
    steps: list[Step] = Field(
        ...,
        description="List of steps to add to the task plan.",
    )
    explanation: str = Field(
        ...,
        description="Explanation for the list of steps.",
    )

def create_task_plan(steps, explanation):
    """ Creates a task plan for the current task. """
    return steps


tool = client.tools.upsert_from_function(
    func=create_task_plan,
    args_schema=StepsList
)

Note: this path for updating tools is currently only supported in Python.

Creating a tool from a file

You can also define a tool from a file that contains source code. For example, you may have the following file:

custom_tool.py

from typing import List, Optional
from pydantic import BaseModel, Field


class Order(BaseModel):
    order_number: int = Field(
        ...,
        description="The order number to check on.",
    )
    customer_name: str = Field(
        ...,
        description="The customer name to check on.",
    )

def check_order_status(
    orders: List[Order]
):
    """
    Check status of a provided list of orders

    Args:
        orders (List[Order]): List of orders to check

    Returns:
        str: The status of the order (e.g. cancelled, refunded, processed, processing, shipping).
    """
    # TODO: implement
    return "ok"

Then, you can define the tool in Letta via the source_code parameter:

TypeScript

import * as fs from "fs";

const tool = await client.tools.create({
  source_code: fs.readFileSync("custom_tool.py", "utf-8"),
});

Python

tool = client.tools.create(
    source_code = open("custom_tool.py", "r").read()
)

Note that in this case, check_order_status will become the name of your tool, since it is the last Python function in the file. Make sure it includes a Google Style Python docstring to define the tool’s arguments and description.

(Advanced) Accessing the Letta API

Custom tools can access the Letta API directly using client injection. Your tools automatically receive:

• Environment variables: LETTA_AGENT_ID, LETTA_PROJECT_ID, LETTA_API_KEY
• Pre-initialized client: A client object with full API access

This enables powerful use cases like dynamic memory management, subagent creation, and multi-agent coordination.

def get_my_memory() -> dict:
    """
    Retrieve the current agent's memory blocks.

    Returns:
        dict: Memory block information
    """
    import os

    # Use auto-injected environment variable
    agent_id = os.environ.get('LETTA_AGENT_ID')

    # Use pre-initialized client (no import needed)
    agent = client.agents.retrieve(agent_id=agent_id)

    memory_info = {}
    for block in agent.memory.blocks:
        memory_info[block.label] = block.value

    return memory_info

For more examples and details, see Sandbox Execution with Client Injection.

Alternatively, you can use client-side tools for tools that need access to local resources or require human-in-the-loop approval.