# Models, harnesses and tools

An agent is easier to understand when its reasoning, execution loop and machine are separate concepts.

## Four pieces, four responsibilities

| Piece | Responsibility |
| --- | --- |
| Model | Generate the next response or action request |
| Harness | Coordinate the execution loop |
| Tool | Perform a defined action |
| Machine | Provide the execution environment |

## Give actions a useful boundary

A tool should expose a clear input and result. The harness should preserve failures and operation identifiers so later steps do not invent success from an incomplete response.

## Keep context grounded

Give an agent the resource identifiers, files and observations relevant to the task. Separate an instruction from a document that is merely being read.

## Learn the vocabulary

Open the [Agents glossary category](/docs/glossary?category=agents), or read [MCP](/docs/mcp) for a standard way to expose tools to a client.