Tools are the functional extensions of an agent’s intelligence—they enable agents to go beyond conversation by interacting with third-party applications, retrieving information, performing logic-based operations, and triggering workflows across complex environments.Powered by the tool invocation capabilities of LLMs, agents can dynamically identify and invoke the most relevant tools at runtime, ensuring flexibility, scalability, and precision in task execution.When an agent needs to take action, it:
Identifies the appropriate tool based on the task
Prepares the required parameters
Invokes the tool through the platform
Processes the results
Incorporates the output into its response
Example — Leave Managing Agent:
Tool
Purpose
Get Leave Balance
Invokes an external API to retrieve leave details
Leave Application
Gathers necessary information and applies leaves in the backend system
The Platform supports three tool types, each serving a different purpose—from orchestrating visual workflows to executing custom scripts or invoking remote services.
Workflow Tools: Visual, no-code tools built with drag-and-drop. Best for well-defined, traceable processes.
Code Tools: Custom JavaScript or Python functions. Best for complex logic and dynamic processing.
MCP Tools: Remote functions via Model Context Protocol. Best for enterprise integrations and shared toolsets.
Workflow Tools provide a visual, no-code interface for designing and orchestrating agent actions. Built for clarity and control, they let you define multi-step workflows using an intuitive graphical builder—ideal for standardized, repeatable processes. They support both synchronous and asynchronous execution modes.Best suited for: Scenarios where business logic is consistent, well-defined, and benefits from visual traceability.
Example
What it does
Weather API tool
Retrieves live weather updates
Stock Market tool
Fetches real-time stock prices
Database Query tool
Accesses structured data from a company’s database
Code Tools provide maximum flexibility by enabling agents to run custom JavaScript or Python code. They are ideal for handling dynamic logic, conditional processing, or integrations that can’t be captured through pre-defined workflows. Code Tools support synchronous execution and are best when precision, extensibility, or complex algorithms are required.Best suited for: Advanced use cases involving business-specific logic, data transformation, or interaction with complex systems.
Example
What it does
SQL Query Processor
Executes SQL queries on a specified database
Custom Validator
Validates inputs using custom logic before proceeding
MCP Tools connect agents to remote functions hosted on Model Context Protocol (MCP) servers. Following a client-server discovery model, agents can dynamically invoke third-party or proprietary services in real time without embedding logic directly into workflows or code.Once connected, MCP Tools can be selected, configured, versioned, and managed independently—allowing modular and scalable integration across environments. Because they are centrally managed, they support versioning, cross-feature reuse, and simplified development.Best suited for: Seamless integration with external APIs, proprietary platforms, or shared toolsets across teams or organizations.
Example
What it does
Enterprise HR Toolset
A suite of HR tools exposed via MCP
Remote Invoice Processor
Executes billing operations through a secure MCP endpoint
Explains what the tool does. The LLM uses this to decide when to invoke it.
description: | Retrieves the current status of a customer order including shipping information, estimated delivery date, and tracking number. Use when customers ask about their order status.
parameters: order_id: type: string description: The unique order identifier (for example, ORD-12345) required: true include_history: type: boolean description: Whether to include status change history required: false default: false
Created in the Tools section, independent of any app. Once deployed, library tools are accessible across multiple apps and act as templates—when imported into an app, they generate a local copy that can be customized without altering the original.
Reusable across multiple apps.
Importing is restricted to deployed tools from the library.
Changes to the library version do not affect local copies in apps.
Created within a specific Agentic App, or imported from the library into an app. Any modifications apply only to the local copy and do not affect the library version. Changes take effect only after the tool is deployed within the app.
