Documentation Index
Fetch the complete documentation index at: https://askui-docs-streamline-documentation.mintlify.app/llms.txt
Use this file to discover all available pages before exploring further.
Tools let agents do more than UI interaction—read files, call APIs, query databases.
from askui.tools import FileReadTool, FileWriteTool, SaveScreenshotTool
with VisionAgent() as agent:
agent.act(
"Read config.json, fill form with those values",
tools=[FileReadTool("config.json")]
)
from askui.models.shared.tools import Tool
class WeatherTool(Tool):
def __init__(self, api_key: str):
self._api_key = api_key
super().__init__(
name="get_weather",
description="Gets weather for a city.",
input_schema={
"type": "object",
"properties": {
"city": {"type": "string", "description": "City name"}
},
"required": ["city"]
}
)
def __call__(self, city: str) -> str:
# Your API call here
return f"Weather in {city}: 22°C, Sunny"
Usage
weather = WeatherTool(api_key="...")
db = DatabaseTool(db_path="./data.db")
with VisionAgent() as agent:
agent.act(
"Look up customer in database, get weather for their city, fill form",
tools=[weather, db]
)
Best Practices
- Clear descriptions: Tell agent when to use the tool
- Precise input schema: Define required parameters
- Informative returns: Return useful strings, not just “done”
- Handle errors: Return error messages instead of raising exceptions