Developer ToolsetHow Code Comment Quality Checker works
Press Load model once: your browser downloads Gemma 4 E2B instruction-tuned (web build) (2.0 GB) from this site and keeps it in its cache. Then add your text and press Check locally. The model runs on this device using your graphics card, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.
Gemma 4 E2B instruction-tuned (web build) is a small open language model from Google. The tool sends it the instruction below plus your text, asks for a JSON answer with fixed fields, and shows each field as a card. It runs at temperature 0, so the same input gives the same answer on the same device, though different graphics cards can word it slightly differently.
Inputs longer than 6,000 characters are cut to that length before they reach the model, and the result says so. The model only sees what you paste: it does not look anything up.
The instruction the model gets
You review code comments, optionally pasted with the code they describe, the way a careful senior engineer would in code review. Judge whether each comment explains why and not just what, whether it matches what the code actually does, whether it is vague ('fixes stuff', 'magic'), outdated, misleading or noise that restates the code, and whether TODOs name an owner or ticket. Only judge the comments; do not review the rest of the code.
What it returns
- Rating: Exactly one of 'Good', 'Needs work' or 'Misleading', followed by a short reason.
- Problems: Each problem, quoting the comment text it refers to.
- Suggested comment: A clearer replacement comment that describes only behaviour shown in the input.
- Already useful: Parts of the comments that already help a reader and should stay.