Good benchmark results don't mean identical outputs. The task completion rate is the same: both pass the same exercises. The paths the model takes differ, but the end result is the same -> pass the tests
The full benchmarking methodology and tooling will be published alongside the paper.
the benchmarks show no degradation in task completion with the shorter descriptions. We're in the age where frontier LLMs don't need instructions on how to read or edit a file.
The descriptions aren't dynamically summarized either. They're static in the plugin, same every call, every session. Zero overhead, fully deterministic.
This has been validated in over 3000 benchmark runs in OpenCode and I ran the entire Exercism Python practice suite (https://github.com/exercism/python/tree/main/exercises/pract...) with and without the plugin with identical results. An initial dataset is shared in the repo.
Every API call sends the full tool schema for all available tools. In a 10-20 step session, you're paying for the same verbose descriptions over and over. Models don't need a paragraph-long explanation of read on the 15th call.
This plugin slims descriptions to one-liners like "Read file content." while cutting 21-45% of token usage. No schema changes, no custom tools. Just trimmed boilerplate as an opt-in plugin.
I made a benchmark on the top tier models as this is not the case in the article. Also I did several cases and the result is self speaking. Hashline is not an improvement that speaks for itself. It is the overhead of harness itself in tool descriptions and schemas. Here are my benchmark results and also my repo for a plugin to truely reduce token usage in top tier models: https://github.com/ASidorenkoCode/openslimedit
The full benchmarking methodology and tooling will be published alongside the paper.