Skip to main content
"""
Single Tool Call Reliability Evaluation
=======================================

Demonstrates reliability checks for one expected tool call.
"""

from typing import Optional

from agno.agent import Agent
from agno.eval.reliability import ReliabilityEval, ReliabilityResult
from agno.models.openai import OpenAIChat
from agno.run.agent import RunOutput
from agno.tools.calculator import CalculatorTools


# ---------------------------------------------------------------------------
# Create Evaluation Function
# ---------------------------------------------------------------------------
def factorial():
    agent = Agent(
        model=OpenAIChat(id="gpt-5.2"),
        tools=[CalculatorTools()],
    )
    response: RunOutput = agent.run("What is 10! (ten factorial)?")
    evaluation = ReliabilityEval(
        name="Tool Call Reliability",
        agent_response=response,
        expected_tool_calls=["factorial"],
    )
    result: Optional[ReliabilityResult] = evaluation.run(print_results=True)
    if result:
        result.assert_passed()


# ---------------------------------------------------------------------------
# Run Evaluation
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    factorial()

​
Run the Example

# Clone and setup repo
git clone https://github.com/agno-agi/agno.git
cd agno/cookbook/09_evals/reliability/single_tool_calls

# Create and activate virtual environment
./scripts/demo_setup.sh
source .venvs/demo/bin/activate

python calculator.py