In the future, assistive social robots will collaborate with humans in a variety of settings. Robots will not only follow human orders but will likely also instruct users during certain tasks. Such robots will inevitably encounter user uncertainty and hesitations. They will continuously need to repair mismatches in common ground in their interactions with humans. In this work, we argue that social robots should instruct humans following the principle of least-collaborative-effort. Like humans do when instructing each other, robots should minimise information efficiency over the benefits of collaborative interactive behaviour. In this paper, we first introduce the concept of least-collaborative-effort in human communication and then discuss implications for design of instructions in human-robot collaboration.