Interactive reasoning tools are usually driven by an agenda of tasks to perform, rather than by conventions of human dialogue. On the other hand, theories of dialogue in natural language tend to ignore the constraints imposed by reasoning tools. This paper presents a system composed of a reasoning module and a dialogue manager which cooperate to produce dialogues that are suitable for reasoning and follow human dialogue conventions. The dialogue manager is driven by focus rules. Various competing focus theories exist but there have been few comparative studies of their use in non-trivial tasks. We make a comparative study of the use of focus theories, which requires us to be precise about our interpretation of our chosen focus theories, and to develop an innovative means of empirical testing for them. We evaluate the theories on an example of combined dialogue and reasoning from the domain of requirements elicitation.