> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-docs-scavio-google-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Tool Call Compression

> Demonstrates team-level tool result compression in both sync and async workflows.

```python tool_call_compression.py theme={null}
"""
Tool Call Compression
=============================

Demonstrates team-level tool result compression in both sync and async workflows.
"""

import asyncio
from textwrap import dedent

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIResponses
from agno.team import Team
from agno.tools.websearch import WebSearchTools

# ---------------------------------------------------------------------------
# Create Members
# ---------------------------------------------------------------------------
sync_tech_researcher = Agent(
    name="Alex",
    role="Technology Researcher",
    model=OpenAIResponses(id="gpt-5.2"),
    instructions=dedent("""
        You specialize in technology and AI research.
        - Focus on latest developments, trends, and breakthroughs
        - Provide concise, data-driven insights
        - Cite your sources
    """).strip(),
)

sync_business_analyst = Agent(
    name="Sarah",
    role="Business Analyst",
    model=OpenAIResponses(id="gpt-5.2"),
    instructions=dedent("""
        You specialize in business and market analysis.
        - Focus on companies, markets, and economic trends
        - Provide actionable business insights
        - Include relevant data and statistics
    """).strip(),
)

async_tech_specialist = Agent(
    name="Tech Specialist",
    role="Technology Researcher",
    model=OpenAIResponses(id="gpt-5.2"),
    instructions=dedent("""
        You specialize in technology and AI research.
        - Focus on latest developments, trends, and breakthroughs
        - Provide concise, data-driven insights
        - Cite your sources
    """).strip(),
)

async_business_analyst = Agent(
    name="Sarah",
    role="Business Analyst",
    model=OpenAIResponses(id="gpt-5.2"),
    instructions=dedent("""
        You specialize in business and market analysis.
        - Focus on companies, markets, and economic trends
        - Provide actionable business insights
        - Include relevant data and statistics
    """).strip(),
)

# ---------------------------------------------------------------------------
# Create Team
# ---------------------------------------------------------------------------
sync_research_team = Team(
    name="Research Team",
    model=OpenAIResponses(id="gpt-5.2"),
    members=[sync_tech_researcher, sync_business_analyst],
    tools=[WebSearchTools()],  # Team uses DuckDuckGo for research
    description="Research team that investigates topics and provides analysis.",
    instructions=dedent("""
        You are a research coordinator that investigates topics comprehensively.

        Your Process:
        1. Use DuckDuckGo to search for a lot of information on the topic.
        2. Delegate detailed analysis to the appropriate specialist
        3. Synthesize research findings with specialist insights

        Guidelines:
        - Always start with web research using your DuckDuckGo tools. Try to get as much information as possible.
        - Choose the right specialist based on the topic (tech vs business)
        - Combine your research with specialist analysis
        - Provide comprehensive, well-sourced responses
    """).strip(),
    db=SqliteDb(db_file="tmp/research_team.db"),
    compress_tool_results=True,
    show_members_responses=True,
)

async_research_team = Team(
    name="Research Team",
    model=OpenAIResponses(id="gpt-5.2"),
    members=[async_tech_specialist, async_business_analyst],
    tools=[WebSearchTools()],  # Team uses DuckDuckGo for research
    description="Research team that investigates topics and provides analysis.",
    instructions=dedent("""
        You are a research coordinator that investigates topics comprehensively.

        Your Process:
        1. Use DuckDuckGo to search for a lot of information on the topic.
        2. Delegate detailed analysis to the appropriate specialist
        3. Synthesize research findings with specialist insights

        Guidelines:
        - Always start with web research using your DuckDuckGo tools. Try to get as much information as possible.
        - Choose the right specialist based on the topic for analysis (tech vs business)
        - Combine your research with specialist analysis
        - Provide comprehensive, well-sourced responses
    """).strip(),
    db=SqliteDb(db_file="tmp/research_team2.db"),
    markdown=True,
    show_members_responses=True,
    compress_tool_results=True,
)


async def run_async_tool_compression() -> None:
    await async_research_team.aprint_response(
        "What are the latest developments in AI agents? Which companies dominate the market? Find the latest news and reports on the companies.",
        stream=True,
    )


# ---------------------------------------------------------------------------
# Run Team
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # --- Sync ---
    sync_research_team.print_response(
        "What are the latest developments in AI agents? Which companies dominate the market? Find the latest news and reports on the companies.",
        stream=True,
    )

    # --- Async ---
    asyncio.run(run_async_tool_compression())
```

## Run the Example

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

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

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

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

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

Full source: [cookbook/03\_teams/10\_context\_compression/tool\_call\_compression.py](https://github.com/agno-agi/agno/blob/main/cookbook/03_teams/10_context_compression/tool_call_compression.py)