Local features are essential to many modern downstream applications. Therefore, it is of interest to determine the properties of local features that contribute to the downstream performance for a better design of keypoint detectors and descriptors. In our work, we propose a new theoretical model for scoring keypoints in the context of the two-view geometry estimation problem. The model determines two properties that a keypoint good for solving the homography estimation problem should have: be repeatable and have a small expected measurement error. The developed theory provides key insights into why maximizing the number of correspondences doesn't always lead to better homography estimates. We use the theoretical results to design a method that detects keypoints good for the homography estimation problem introducing the Bounded NeSS-ST (BoNeSS-ST) keypoint detector. The novelty of BoNeSS-ST comes from i) strong theoretical foundations, ii) a more accurate keypoint scoring due to subpixel refinement and iii) a cost designed for superior robustness to low-saliency keypoints. As a result, BoNeSS-ST outperforms prior self-supervised local feature detectors in both planar homography and epipolar geometry estimation problems.