Call shorts.judge_cut

Play back Goosy's verdict on its own edit of a short — 'is this cut any good', 'how does this edit hold up'. Read back Goosy's verdict on its own edit of a short — whether the hook lands in the first second, whether it holds to the end, whether it reads with the sound off, whether anything sits on a face, and how it ends. The verdict is written when the short is edited; this reports it. Say the ONE line out loud and never a score. Not for the list of changes the edit made — that is shorts.read_edit. Over the API it answers in two calls: without confirmation_id it proposes — says what would happen, returns a confirmation_id and changes, spends and sends nothing; the same arguments again with that confirmation_id, on a member's own API key, do it.

Every result names the workspace it ran in. Say which workspace the answer is about. When the account has more than one workspace and none is selected, this tool refuses with workspace_ambiguous and lists the choices — offer them, never pick one.