> ## Documentation Index
> Fetch the complete documentation index at: https://phidatainc.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent-with-Tool Instantiation Performance Evaluation

> Measure runtime and memory of 1000 Agno Agent constructions using OpenAIChat gpt-4o plus a weather tool.

Demonstrates measuring instantiation performance for a tooled agent.

```python instantiate_agent_with_tool.py theme={null}
"""
Agent-with-Tool Instantiation Performance Evaluation
====================================================

Demonstrates measuring instantiation performance for a tooled agent.
"""

from typing import Literal

from agno.agent import Agent
from agno.eval.performance import PerformanceEval
from agno.models.openai import OpenAIChat


# ---------------------------------------------------------------------------
# Create Benchmark Tool
# ---------------------------------------------------------------------------
def get_weather(city: Literal["nyc", "sf"]):
    """Use this to get weather information."""
    if city == "nyc":
        return "It might be cloudy in nyc"
    elif city == "sf":
        return "It's always sunny in sf"


tools = [get_weather]


# ---------------------------------------------------------------------------
# Create Benchmark Function
# ---------------------------------------------------------------------------
def instantiate_agent():
    return Agent(model=OpenAIChat(id="gpt-4o"), tools=tools)  # type: ignore


# ---------------------------------------------------------------------------
# Create Evaluation
# ---------------------------------------------------------------------------
instantiation_perf = PerformanceEval(
    name="Agent Instantiation", func=instantiate_agent, num_iterations=1000
)

# ---------------------------------------------------------------------------
# Run Evaluation
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    instantiation_perf.run(print_results=True, print_summary=True)
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno memory-profiler openai
    ```
  </Step>

  <Step title="Run the example">
    Save the code above as `instantiate_agent_with_tool.py`, then run:

    ```bash theme={null}
    python instantiate_agent_with_tool.py
    ```
  </Step>
</Steps>

Full source: [cookbook/09\_evals/performance/instantiate\_agent\_with\_tool.py](https://github.com/agno-agi/agno/blob/main/cookbook/09_evals/performance/instantiate_agent_with_tool.py)