instead of processing after the fact, process before you load, and add the extracted value to one of the metadata fields of the image file. when you load the image file in iNaturalist, the system can load the image metadata and map it to the resulting observation’s description, tag list, or an observation field.
see https://forum.inaturalist.org/t/photographs-metadata-which-specific-eg-exif-fields-get-checked-during-photographs-upload-please/41467/3 for more information about how the image metadata is mapped to the observation.