Create an API tool

API tools are used to integrate external services and automate workflows.

Quickly create an API tool

1. Go to the tool management interface

First, please enter the " AI Features" section, then click "🔧 Tools". After entering the tool list page, click the "➕ Add Tool" button in the top right corner.

2. Choose tool type

For tool type, select API.

3. Set display name

Set a clear display name for the tool, here set as google calendar.

• Purpose: This name will be shown in the platform interface for all users to see.

• Recommendation: Choose a name that clearly expresses the main function of the tool to help users understand. There is no strict format requirement for this name.

4. Set tool name

Next is the "Tool Name" field.

• Purpose: This name is the unique identifier the AI assistant uses internally to call and identify this tool.

• Naming rules (important):

  • Must use English.

  • Can only include:

    • Lowercase letters (a-z)

    • Uppercase letters (A-Z)

    • Digits (0-9)

    • Underscore (_)

    • Hyphen (-)

  • Examples:get_weather_forecast, database-query-tool

The image below is set to google_calendar_retriever

5. Write tool description

In the "Tool Description" field, users can provide a clear and detailed description of the tool.

• Importance: A good description helps the AI assistant more accurately understand:

  • The tool's functions and purpose.

  • When this tool should be used.

  • How to interpret the tool's output.

• Suggested content: Explain what the tool does, what inputs it takes, what outputs it produces, and any usage notes.

6. API configuration details

a. 🔗 API URL

• Fill in the full URL of the target API endpoint (including http:// or https://).

• Examples:https://api.opencalendar.org/data/2.5

b. 📮 HTTP method

• Select the HTTP verb required by the API service from the dropdown:

  • GET: Typically used to retrieve resources.

  • POST: Typically used to create new resources or submit data.

  • PUT: Typically used to fully replace or update resources.

  • DELETE: Typically used to delete resources.

c. 📰 Headers

• Click "➕ Add Header" to define HTTP headers sent with the request.

• Format: Must be a valid JSON object where the key is the header name and the value is the header content (string).

• Common uses:

  • Authentication (Authorization, X-API-Key)

  • Specify content type (Content-Type)

  • Specify accepted response format (Accept)

• Examples:

  Copy

  {
    "Content-Type": "application/json; charset=utf-8",
    "Authorization": "Bearer {{SECRET_API_TOKEN}}",
    "Accept": "application/vnd.github.v3+json"
  }

d. 🧩 Parameters Schema

• Core settings: Define which parameters the AI assistant can or must provide when calling this tool, and the format of those parameters.

• Format: Use the standard JSON Schema format.

• Key elements:

  • type: "object": Indicates the parameters are an object.

  • properties: Defines the object for each parameter.

    • Parameter name (for example "search"): The corresponding object contains details about that parameter.

      • type: The data type of the parameter (string, integer, number, boolean, array, object).

      • description: Explanation to the AI assistant describing the meaning of this parameter.

      • default (optional): The default value of the parameter.

      • enum (optional): If the parameter value can only be one of specific options, list them here.

  • required: An array containing allrequiredparameter names.

• Examples (For media search tool):

  Copy

  {
      "type": "object",
      "properties": {
          "limit": {
              "type": "integer",
              "minimum": 1,
              "description": "Maximum number of returned results"
          },
          "fields": {
              "type": "string",
              "description": "Comma-separated list of fields"
          },
          "search": {
              "type": "string",
              "description": "Search keywords"
          }
      },
      "required": ["search"]
  }

7. 💾 Save tool

After confirming all settings are correct, scroll to the bottom of the page and click the "Confirm" button. Your new tool is now created!

⚠️ Important reminder

Connection test

• After creating the tool, it is recommended to test whether the API works properly

• You can use testing tools to validate tool functionality, such as:

  • POSTMAN

  • An API testing request platform built by the company itself

Permission management

• Regularly check tool usage and permission settings

Troubleshooting

• If the connection fails, check the error code to see the cause of the error

• Confirm that headers and parameter structure meet the requirements