context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Why it matters
Making the model write ordinary code against typed capabilities, instead of learning a new JSON schema per action, cuts always-loaded schema tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → sharply and makes the logic between calls deterministic — with security enforced below the model.
