1Identity
A name, an ID and a description.
The description is what gets work sent to this agent. When several agents are available, the planner reads each description to decide which one should take a step, so it says what the agent does, when to use it and when not to.
2Instructions
The agent's standing orders, in plain language.
How it should answer, what it must always include, what it must never do. Examples can be added to show the kind of answer you expect.
3Tools
Which tools the agent may call.
Per system, choose all tools, which includes tools added later, or select a fixed list. Tools that change data carry a "write" badge and a warning, and the screen shows how much of the model's context the selection uses.
4Execution
How the agent goes about its work.
Answer in one pass, or plan first and then work through the plan. A limit on the number of steps stops a run that is going nowhere.
5Guardrails
What the agent may see and do.
Read-only, approval before chosen tools run, and rules for sensitive data. Read about guardrails.
6Skills
Written procedures the agent can follow.
A skill is a short document that explains how to do a particular job, for example how to triage a late order. The agent opens the skills that fit the request.