Harness is an appropriate name. It comes from reinforcement learning world where you need to build the proper scaffolding for it to optimize for the goal you want it to.

This is very similar to what the agent is doing. You are building the appropriate environment for it to be able to complete the task most reliably etc

Not just functions/tools and documentation available (which is similar to a library), also context and critically, enforcement of behavior.

This is probably the key thing that makes it a "harness". If the agent can do whatever it wants, it's not in a harness.