# Tool result offloading keeps large outputs out of the model's context

> Set offload_tool_results=True and any tool result over 16,000 characters goes to AgentFS instead of into context, leaving a short envelope with a preview, the size, and a result_id the agent can read or search on demand.

- Published: 2026-08-24
- Author: Ashpreet Bedi
- Categories: Changelog
- Canonical: https://www.agno.com/articles/tool-result-offloading-keeps-large-outputs-out-of-the-models-context
- Markdown: https://www.agno.com/articles/tool-result-offloading-keeps-large-outputs-out-of-the-models-context.md

Tool result offloading writes an oversized tool result to storage instead of into the model's context. Set `offload_tool_results=True` and any result over 16,000 characters goes to `AgentFS`, leaving a short envelope in the message with a preview, the size, and a `result_id`. The agent gets `read_result` and `search_result` to fetch the rest only when it needs it, and nothing calls a model on the write path.

Previously, a large tool result landed in context in full and stayed there, consuming your window and adding tokens to every turn that followed. Now the agent carries a compact reference by default and pulls the full result, or searches inside it, on demand.

You can tune when offloading happens and how long results are kept with `ResultStore(threshold_chars=..., ttl_seconds=...)`.

Turn it on when you create an agent:

```python
from agno.agent import Agent

agent = Agent(offload_tool_results=True)
```

View the [Result Offloading docs](https://docs.agno.com/examples/agents/result-offloading/offload-tool-results#offload-tool-results). See the [cookbook](https://github.com/agno-agi/agno/tree/main/cookbook/02_agents/22_result_offloading) for reference.
