Skip to main content

​
Basic Usage

Add tools to agents as functions or Tool objects: 
def get_weather(location: str) -> str:
    """Get weather for a location."""
    return f"Weather in {location}: 22°C"

agent = Agent(
    name="weather_agent",
    model="openai/gpt-4o-mini",
    tools=[get_weather]  # Function automatically becomes a tool
)

​
Tool Configuration

Use Tool for custom descriptions and parameter control: 
from timbal import Tool

# Custom description - helpful when function name isn't clear enough
Tool(
    handler=get_weather,
    description="Get current weather information for any location"
)
When a tool has many parameters, use schema_params_mode="required" to reduce tokens and avoid overwhelming the LLM with unnecessary options: 
Tool(
    handler=search,
    schema_params_mode="required"  # Only show required params (default: "all")
)
You can also include or exclude specific parameters to fine-tune what the LLM sees: 
# Include extra parameters even in "required" mode
Tool(
    handler=search_function,
    schema_params_mode="required",
    schema_include_params=["model"]  # Include this optional param
)

# Exclude sensitive or internal parameters
Tool(
    handler=api_function,
    schema_exclude_params=["api_key", "debug_mode"]  # Hide from LLM
)
Set default values that are automatically applied when the tool is called: 
Tool(
    handler=database_query,
    default_params={
        "timeout": 30
    }  # These values are used when not specified by the LLM
)
You can also use functions or environment variables as default parameters: 
def get_current_timestamp():
    return datetime.now().isoformat()

def process_data(data: str, timestamp: str | None = None, user_id: str = "default"):
    return f"Processed {data} at {timestamp} by {user_id}"

# Tool with dynamic default parameters
tool = Tool(
    name="data_processor",
    handler=process_data,
    default_params={
        "timestamp": get_current_timestamp,
        "user_id": "system_user"
    }
)

​
Agent as a Tool

You can use an Agent as a tool within another Agent, enabling hierarchical agent compositions where specialized agents handle specific tasks. Since Agent instances can be treated as Tool objects, they inherit the same parameter control configurations available to regular tools. 
from timbal import Agent

def calculate_cost(days: int, hotel_rate: float, flights: float = 0) -> float:
    """Calculate total trip cost."""
    return (days * hotel_rate) + flights

# Pricing specialist agent
pricing_agent = Agent(
    name="pricing_calculator",
    description="Calculate travel costs",  # Tool description for other agents
    model="openai/gpt-4o-mini",
    system_prompt="Answer only with the price. Any text",
    tools=[calculate_cost]
)

# Main travel agent
travel_agent = Agent(
    name="travel_assistant", 
    model="openai/gpt-4o",
    system_prompt="Help plan trips and provide travel advice.",
    tools=[pricing_agent]
)

​
Summary

  • Automatic Introspection: Function signatures become tool schemas automatically
  • Enhanced Validation: Pydantic-based parameter validation
  • Execution Flexibility: Support for all Python callable types
  • Better Configuration: Fine-grained parameter control
  • Performance: Concurrent execution and optimized patterns
  • Robustness: Improved error handling and tracing
For more advanced patterns, see the Integrations and explore the built-in tools in the Timbal library!