OpenRouter improves tool selection for Claude Code and Codex on its server
Overview
OpenRouter says it made its server's tools easier for agents to understand and select, added structured output where it matters, and has the server tell Claude Code and Codex when to use them.
In OpenRouter's own runs, Claude Code completed 8 of 8 tasks, up from 5 of 8. The post also cites a score of 100/100 from @manufact for the work.
The figures come from OpenRouter's own post and a score attributed to @manufact; the report does not describe the tasks or the scoring method.
Written by AI from the articles below · updated Nov 9, 4:16 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
OpenRouter@OpenRouterOfficialOpenRouter improves agent ergonomics so Claude Code and Codex pick its tools betterAIOpenRouter says it made its tools easier for agents to understand and select, added structured output where it matters, and has its server tell Claude Code and Codex when to use them. In its runs, Claude Code went from 5/8 tasks to 8/8, and @manufact scores the work 100/100.

Heat Trend
- Current comparable heat
- 8
- Peak comparable heat
- 9Nov 9, 5:00 PM ET
- Change in past 24 hours
- –
The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.