The authors propose a representation of positioning uncertainty for robot manipulation tasks and a method by which it can be propagated through robot programs. The objective is to integrate error propagation and analysis into a task-level programming system in order to produce robust programs. This integration is discussed with reference to an example. The method consists of evaluating progressively the uncertainty through a sequence of actions and maintaining a symbolic trace of computations. When a constraint is violated, the system determines the predominant source of uncertainty in order to guide the planning process. >