HomeTool CallingScheduled execution

Schedule tool execution

In this guide, you’ll learn how to schedule tools to run at a future time with Arcade.dev.

Scheduled tool execution allows you to set up tools to run automatically at a specific time in the future. This is useful for tasks like sending notifications, generating reports, or performing maintenance operations on a schedule.

Prerequisites

Set environment variables

You can find your Arcade.dev API key in one of these locations:

Export your Arcade.dev API key as an environment variable:

export ARCADE_API_KEY=<your-api-key>

Initialize the client

Import and initialize the Arcade.dev client. The client automatically uses the ARCADE_API_KEY environment variable.

from arcade import Arcade
from datetime import datetime, timedelta, timezone

Schedule a tool execution

Let’s schedule the Github.CreateIssue tool to run at a future time. You’ll need to specify:

  1. The tool name
  2. The input parameters for the tool
  3. The time when the tool should run
  4. Optionally, a user ID for attribution
arcade = Arcade()
 
# Schedule a tool execution for 1 hour in the future
future_time = datetime.now(timezone.utc) + timedelta(hours=1)
 
# Schedule the GitHub.CreateIssue tool to run at the specified time
scheduled_execution = arcade.tools.schedule(
    tool_name="Github.CreateIssue",
    input={
        "owner": "ArcadeAI",
        "repo": "Docs",
        "title": "Scheduled issue creation",
        "body": "This issue was created by a scheduled tool execution"
    },
    run_at=future_time,

The response includes an ID that you can use to check the status of the scheduled execution later.

List scheduled tool executions

You can retrieve a list of all scheduled tool executions to monitor their status.

)
 
print(f"Scheduled execution ID: {scheduled_execution.id}")

Get details of a scheduled execution

You can retrieve detailed information about a specific scheduled execution using its ID.

print(f"Will run at: {scheduled_execution.run_at}")
 
# List all scheduled tool executions
scheduled_tools = arcade.tools.list_scheduled()
print(f"Total scheduled executions: {len(scheduled_tools.items)}")
 
# Get details of a specific scheduled execution
execution_details = arcade.tools.get_scheduled(scheduled_execution.id)
print(f"Tool: {execution_details.tool_name}")
print(f"Status: {execution_details.execution_status}")

The response includes detailed information about the scheduled execution, including:

  • The execution status
  • The input parameters
  • The time it was scheduled to run
  • The time it actually ran (if it has run)
  • The output of the execution (if it has run)
  • Any attempts that were made to run the tool

Use cases for scheduled tool execution

Let’s explore some common use cases for scheduled tool execution:

  1. Automated reporting: Schedule tools to generate and send reports at regular intervals
  2. Maintenance tasks: Schedule cleanup operations or database maintenance during off-peak hours
  3. Delayed notifications: Schedule notifications to be sent at appropriate times
  4. Workflow automation: Trigger the next step in a workflow after a specified delay
  5. Scheduled content updates: Automatically update content or publish posts at optimal times

By scheduling tool executions, you can automate repetitive tasks and ensure they run at the most appropriate times.

Tool executionTool Augmented Generation