One of those 'things usually left out' is how much the games complexity requires the situational information to be processed and boiled down into the symbolic form to have these methods applied - to be cached (and constantly patched in a dynamic situation) or regenerated on-demand(where early pruninig helps).
The more complex and interrelated the game state is (possibly with temporal issues where a trend pattern is an indicator) and with uncertainty ontop of that (imperfect info, as well as independantly acting entities) the more work (processing resource) that evaluation becomes.
Which of GOAP/MCTS can do the most EARLY exclusion to narrow down the situational space being considered and evaluated would indicate its utility. Boiling down all the factors to be easily compared (in prioritizing and picking candidate solutions) can be the very hard part. Spatial positionality on a map itself might seem an easy shortcutted data set, but consider evaluating the patterns in GO - the analysis for even such a simple 'terrain' and entity mechanics explodes in the processing required to evaluate the actual situations.
Yes it would seem like the two methods have similar requirements here. Geometric space in a game has to be given a reasonable representation. World coordinates need to be abstracted to a minimum number of pixels, meters or kilometers in order for the planners to ever be able to finish. For real time games, time also needs to be abstracted to a minimum duration. Perhaps doing this abstraction work can be considered a form of pruning where actions and state changes that are very close to each other are considered the same.