# Tool result

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: tool output, tool response, function result, tool results, observation

What comes back to the model after it uses a tool: a file's contents, the output of a command, a search result or an error. Tool results are the [agent](https://ecosystem.samcarlton.com/ai-agent)'s only view of the world, and long ones fill the [context window](https://ecosystem.samcarlton.com/context-window) quickly.

**For example:** The [agent](https://ecosystem.samcarlton.com/ai-agent) runs the tests, the tool result shows three failures and their causes, and the agent's next step is to fix those three.

## Connects to (6)

- [Tool use](https://ecosystem.samcarlton.com/tool-use): A way for a model to ask the software around it to run a defined action, such as a search or a database lookup, and send back the result.
- [Agent environment](https://ecosystem.samcarlton.com/agent-environment): Everything outside the agent's own software that it can look at or change: your files, terminal, browser, databases and connected services.
- [Context window](https://ecosystem.samcarlton.com/context-window): How much text an LLM can take into account at one time.
- [Input tokens](https://ecosystem.samcarlton.com/input-tokens): The tokens an AI product sends to the model on each request: the instructions, the conversation so far, files and tool results.
- [AI agent](https://ecosystem.samcarlton.com/ai-agent): An AI tool that does more than answer a question.
- [Contextual knowledge](https://ecosystem.samcarlton.com/contextual-knowledge): Facts the model can read directly in front of it right now, such as documents you pasted, files the agent opened or search results.

Map view: https://ecosystem.samcarlton.com/tool-result