Why does the agent only return the `ToolCallSummaryMessage` type tool result after invoking the tool, instead of a `TextMessage` type summary? #7114

code-isnot-cold · 2025-11-11T03:21:50Z

code-isnot-cold
Nov 11, 2025

I am studying the official examples, and I notice that the agent with tools directly returns the result of the tool call instead of passing the tool result back to the LLM for another summary. Is this a feature of the Autogen framework? How can one implement it so that the LLM summarizes the result returned by the tool?

Official example：https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/agents.html#getting-result

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.messages import StructuredMessage
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient

# Define a tool that searches the web for information.
# For simplicity, we will use a mock function here that returns a static string.
async def web_search(query: str) -> str:
    """Find information on the web"""
    return "AutoGen is a programming framework for building multi-agent applications."


# Create an agent that uses the OpenAI GPT-4o model.
model_client = OpenAIChatCompletionClient(
    model="gpt-4.1-nano",
    # api_key="YOUR_API_KEY",
)
agent = AssistantAgent(
    name="assistant",
    model_client=model_client,
    tools=[web_search],
    system_message="Use tools to solve tasks.",
)

# Use asyncio.run(agent.run(...)) when running in a script.
result = await agent.run(task="Find information on AutoGen")
print(result.messages)

[TextMessage(source='user', models_usage=None, metadata={}, content='Find information on AutoGen', type='TextMessage'), ToolCallRequestEvent(source='assistant', models_usage=RequestUsage(prompt_tokens=61, completion_tokens=16), metadata={}, content=[FunctionCall(id='call_703i17OLXfztkuioUbkESnea', arguments='{"query":"AutoGen"}', name='web_search')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='assistant', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='AutoGen is a programming framework for building multi-agent applications.', name='web_search', call_id='call_703i17OLXfztkuioUbkESnea', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='assistant', models_usage=None, metadata={}, content='AutoGen is a programming framework for building multi-agent applications.', type='ToolCallSummaryMessage')]

It can be seen that the last piece of information is of the ToolCallSummaryMessage type, and it is consistent with the function result. The LLM did not summarize and return it to the user again.

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Why does the agent only return the `ToolCallSummaryMessage` type tool result after invoking the tool, instead of a `TextMessage` type summary? #7114

Uh oh!

{{title}}

Uh oh!

Replies: 0 comments

Select a reply

Uh oh!

Why does the agent only return the ToolCallSummaryMessage type tool result after invoking the tool, instead of a TextMessage type summary? #7114

Uh oh!

code-isnot-cold Nov 11, 2025

Replies: 0 comments

Why does the agent only return the `ToolCallSummaryMessage` type tool result after invoking the tool, instead of a `TextMessage` type summary? #7114

code-isnot-cold
Nov 11, 2025