dify-docs/plugin-dev-en/0411-tool.mdx

---
dimensions:
  type:
    primary: reference
    detail: core
  level: beginner
standard_title: Tool
language: en
title: Tool Return
description: This document provides a detailed introduction to the data structure
  and usage of Tools in Dify plugins. It covers how to return different types of messages
  (image URLs, links, text, files, JSON), how to create variable and streaming variable
  messages, and how to define tool output variable schemas for reference in workflows.
---

## Overview

<Note>
Before diving into the detailed interface documentation, make sure you have a general understanding of the tool integration process for Dify plugins.
</Note>

<CardGroup cols={2}>
  <Card title="Message Types" icon="comment-dots" href="#message-return">
    Return different types of messages such as text, links, images, and JSON
  </Card>
  <Card title="Variables" icon="code-branch" href="#variable">
    Create and manipulate variables for workflow integration
  </Card>
  <Card title="Output Schema" icon="diagram-project" href="#returning-custom-variables">
    Define custom output variables for workflow references
  </Card>
</CardGroup>

## Data Structure

### Message Return

<Info>
Dify supports various message types such as `text`, `links`, `images`, `file BLOBs`, and `JSON`. These messages can be returned through specialized interfaces.
</Info>

By default, a tool's output in a workflow includes three fixed variables: `files`, `text`, and `json`. The methods below help you populate these variables with appropriate content.

<Tip>
While you can use methods like `create_image_message` to return an image, tools also support custom output variables, making it more convenient to reference specific data in a workflow.
</Tip>

### Message Types

<CodeGroup>
```python Image URL
def create_image_message(self, image: str) -> ToolInvokeMessage:
    """
    Return an image URL message
    
    Dify will automatically download the image from the provided URL
    and display it to the user.
    
    Args:
        image: URL to an image file
        
    Returns:
        ToolInvokeMessage: Message object for the tool response
    """
    pass
```

```python Link
def create_link_message(self, link: str) -> ToolInvokeMessage:
    """
    Return a clickable link message
    
    Args:
        link: URL to be displayed as a clickable link
        
    Returns:
        ToolInvokeMessage: Message object for the tool response
    """
    pass
```

```python Text
def create_text_message(self, text: str) -> ToolInvokeMessage:
    """
    Return a text message
    
    Args:
        text: Text content to be displayed
        
    Returns:
        ToolInvokeMessage: Message object for the tool response
    """
    pass
```

```python File
def create_blob_message(self, blob: bytes, meta: dict = None) -> ToolInvokeMessage:
    """
    Return a file blob message
    
    For returning raw file data such as images, audio, video, 
    or documents (PPT, Word, Excel, etc.)
    
    Args:
        blob: Raw file data in bytes
        meta: File metadata dictionary. Include 'mime_type' to specify 
              the file type, otherwise 'octet/stream' will be used
              
    Returns:
        ToolInvokeMessage: Message object for the tool response
    """
    pass
```

```python JSON
def create_json_message(self, json: dict) -> ToolInvokeMessage:
    """
    Return a formatted JSON message
    
    Useful for data transmission between workflow nodes.
    In agent mode, most LLMs can read and understand JSON data.
    
    Args:
        json: Python dictionary to be serialized as JSON
        
    Returns:
        ToolInvokeMessage: Message object for the tool response
    """
    pass
```
</CodeGroup>

<Accordion title="Parameters">
  <ParamField path="image" type="string" required>
    URL to an image that will be downloaded and displayed
  </ParamField>
  
  <ParamField path="link" type="string" required>
    URL to be displayed as a clickable link
  </ParamField>
  
  <ParamField path="text" type="string" required>
    Text content to be displayed
  </ParamField>
  
  <ParamField path="blob" type="bytes" required>
    Raw file data in bytes format
  </ParamField>
  
  <ParamField path="meta" type="dict">
    File metadata including:
    - `mime_type`: The MIME type of the file (e.g., "image/png")
    - Other metadata relevant to the file
  </ParamField>
  
  <ParamField path="json" type="dict" required>
    Python dictionary to be serialized as JSON
  </ParamField>
</Accordion>

<Tip>
When working with file blobs, always specify the `mime_type` in the `meta` dictionary to ensure proper handling of the file. For example: `{"mime_type": "image/png"}`.
</Tip>

### Variables

<CodeGroup>
```python Standard Variable
from typing import Any

def create_variable_message(self, variable_name: str, variable_value: Any) -> ToolInvokeMessage:
    """
    Create a named variable for workflow integration
    
    For non-streaming output variables. If multiple instances with the 
    same name are created, the latest one overrides previous values.
    
    Args:
        variable_name: Name of the variable to create
        variable_value: Value of the variable (any Python data type)
        
    Returns:
        ToolInvokeMessage: Message object for the tool response
    """
    pass
```

```python Streaming Variable
def create_stream_variable_message(
    self, variable_name: str, variable_value: str
) -> ToolInvokeMessage:
    """
    Create a streaming variable with typewriter effect
    
    When referenced in an answer node in a chatflow application,
    the text will be output with a typewriter effect.
    
    Args:
        variable_name: Name of the variable to create
        variable_value: String value to stream (only strings supported)
        
    Returns:
        ToolInvokeMessage: Message object for the tool response
    """
    pass
```
</CodeGroup>

<Accordion title="Parameters">
  <ParamField path="variable_name" type="string" required>
    Name of the variable to be created or updated
  </ParamField>
  
  <ParamField path="variable_value" type="Any/string" required>
    Value to assign to the variable:
    - For standard variables: Any Python data type
    - For streaming variables: String data only
  </ParamField>
</Accordion>

<Warning>
The streaming variable method (`create_stream_variable_message`) currently only supports string data. Complex data types cannot be streamed with the typewriter effect.
</Warning>

## Custom Output Variables

<Info>
To reference a tool's output variables in a workflow application, you need to define which variables might be output. This is done using the [JSON Schema](https://json-schema.org/) format in your tool's manifest.
</Info>

### Defining Output Schema

<CodeGroup>
```yaml Tool Manifest with Output Schema
identity:
  author: example_author
  name: example_tool
  label:
    en_US: Example Tool
    zh_Hans: 示例工具
    ja_JP: ツール例
    pt_BR: Ferramenta de exemplo
description:
  human:
    en_US: A simple tool that returns a name
    zh_Hans: 返回名称的简单工具
    ja_JP: 名前を返す簡単なツール
    pt_BR: Uma ferramenta simples que retorna um nome
  llm: A simple tool that returns a name variable
output_schema:
  type: object
  properties:
    name:
      type: string
      description: "The name returned by the tool"
    age:
      type: integer
      description: "The age returned by the tool"
    profile:
      type: object
      properties:
        interests:
          type: array
          items:
            type: string
        location:
          type: string
```
</CodeGroup>

<Accordion title="Schema Structure">
  <ParamField path="output_schema" type="object" required>
    The root object defining your tool's output schema
  </ParamField>
  
  <ParamField path="type" type="string" required>
    Must be "object" for tool output schemas
  </ParamField>
  
  <ParamField path="properties" type="object" required>
    Dictionary of all possible output variables
  </ParamField>
  
  <ParamField path="properties.[variable_name]" type="object">
    Definition for each output variable, including its type and description
  </ParamField>
</Accordion>

<Warning>
Even with an output schema defined, you still need to actually return a variable using `create_variable_message()` in your implementation code. Otherwise, the workflow will receive `None` for that variable.
</Warning>

### Example Implementation

<CodeGroup>
```python Basic Variable Example
def run(self, inputs):
    # Process inputs and generate a name
    generated_name = "Alice"
    
    # Return the name as a variable that matches the output_schema
    return self.create_variable_message("name", generated_name)
```

```python Complex Structure Example
def run(self, inputs):
    # Generate complex structured data
    user_data = {
        "name": "Bob",
        "age": 30,
        "profile": {
            "interests": ["coding", "reading", "hiking"],
            "location": "San Francisco"
        }
    }
    
    # Return individual variables
    self.create_variable_message("name", user_data["name"])
    self.create_variable_message("age", user_data["age"])
    self.create_variable_message("profile", user_data["profile"])
    
    # Also return a text message for display
    return self.create_text_message(f"User {user_data['name']} processed successfully")
```
</CodeGroup>

<Tip>
For complex workflows, you can define multiple output variables and return them all. This gives workflow designers more flexibility when using your tool.
</Tip>

## Examples

### Complete Tool Implementation

<CodeGroup>
```python Weather Forecast Tool
import requests
from typing import Any

class WeatherForecastTool:
    def run(self, inputs: dict) -> Any:
        # Get location from inputs
        location = inputs.get("location", "London")
        
        try:
            # Call weather API (example only)
            weather_data = self._get_weather_data(location)
            
            # Create variables for workflow use
            self.create_variable_message("temperature", weather_data["temperature"])
            self.create_variable_message("conditions", weather_data["conditions"])
            self.create_variable_message("forecast", weather_data["forecast"])
            
            # Create a JSON message for data transmission
            self.create_json_message(weather_data)
            
            # Create an image message for the weather map
            self.create_image_message(weather_data["map_url"])
            
            # Return a formatted text response
            return self.create_text_message(
                f"Weather in {location}: {weather_data['temperature']}°C, {weather_data['conditions']}. "
                f"Forecast: {weather_data['forecast']}"
            )
            
        except Exception as e:
            # Handle errors gracefully
            return self.create_text_message(f"Error retrieving weather data: {str(e)}")
    
    def _get_weather_data(self, location: str) -> dict:
        # Mock implementation - in a real tool, this would call a weather API
        return {
            "location": location,
            "temperature": 22,
            "conditions": "Partly Cloudy",
            "forecast": "Sunny with occasional showers tomorrow",
            "map_url": "https://example.com/weather-map.png"
        }
```
</CodeGroup>

<Tip>
When designing tools, consider both the direct output (what the user sees) and the variable output (what other workflow nodes can use). This separation provides flexibility in how your tool is used.
</Tip>

{/*
Contributing Section
DO NOT edit this section!
It will be automatically generated by the script.
*/}

---

[Edit this page](https://github.com/langgenius/dify-docs/edit/main/plugin-dev-en/0411-tool.mdx) | [Report an issue](https://github.com/langgenius/dify-docs/issues/new?template=docs.yml)