subtraction

The passage around this formula

Put the three costs together and a deployment question comes into focus: given a fixed context window, how many tools can actually be offered before something has to give? A simple ceiling model makes the trade-off explicit. Let C be the model’s usable context window, $T_{\mathrm{system}}$ the fixed cost of operator instructions, and $T_{\mathrm{reserve}}$ a reserved allowance for the user’s message and the model’s own answer. If every tool schema costs on average $\bar{t}_{\mathrm{tool}}$ tokens and all of them are injected in full on every turn, the maximum number of tools a deployment can nominally offer before it must start pruning or retrieving is $n_{\max} = \left\lfloor \frac{C - T_{\mathrm{system}} - T_{\mathrm{reserve}}}{\bar{t}_{\mathrm{tool}}} \right\rfloor$. The assumption doing the…

Read this part in the article →