[alansaber]

This sounds... kind of useless? Really good JSON or similar constrained decoder performance is interesting, but normal decoder > tool validator loop with good error message > tool retry is almost always able to get a tool to work second try, and input is cached so it's not expensive.

[aldanor]

Things are not always that simple, eg https://lucumr.pocoo.org/2026/7/4/better-models-worse-tools/

[winstonp]

The avg coding session has hundreds or thousands of tool calls. Even a 5% failure rate noticeably notches up token use and cost. See Gemini.

[alansaber]

Yes, but each tool call has a different failure %. The tool calls that make up the majority of volume like grep are going to have nowhere near a 5% failure. A custom user-defined skill having a 5% failure rate is probably fine.