How is this check scored?
Every threshold on this page comes from one source: the citation-readiness scorer Gadex publishes. Per Gadex's own build, the weights below are read directly from that scorer and a test fails the build if the documented figure stops matching the applied one. A pass earns the full 6 points, a warning earns half, a fail earns none.
| Result | How it is decided |
|---|---|
| Pass | At least 60 per cent of paragraphs are under 400 characters. |
| Warn | At least 35 per cent are, or the page has fewer than three paragraphs to judge. |
| Fail | Under 35 per cent. |
Why does this check exist?
A long paragraph forces a choice: quote a fragment of it, or summarise the whole thing. Both lose you something — the fragment loses context, the summary loses attribution.
Short paragraphs are individually liftable, which means more of the page is available to be quoted verbatim rather than paraphrased.
The threshold is a proportion, not a maximum. A page is allowed long paragraphs; it should not be made only of them.
How do you fix it?
- Split paragraphs at the point where they change subject. Most over-long paragraphs are two paragraphs that were never separated.
- Where content is genuinely enumerable, use a real list. A run of items inside a paragraph extracts far worse than the same items as list markup.
- Do not shred prose into single sentences. An argument that needs three sentences to hold together should keep them.
How often do pages fail this check?
Per Gadex's own measurement across the 91 content pages on this site, using the checker published at /tools/ai-search-visibility-checker/: 91 pass, 0 carry a warning, and 0 fail. Per that same run, 0 per cent of Gadex pages have something to fix on this check alone.
Those figures include the pages Gadex fails. A checker whose author exempts itself from the checking is marketing rather than measurement, so the numbers are generated from the built site on every deploy and the build fails if the published figures stop matching what Gadex actually scores. When Gadex fixes pages, the numbers move on their own.
What does this check miss?
- The check measures characters, not readability. Three hundred characters of dense jargon passes; 420 characters of clear prose warns.
- It treats list items as paragraphs, so a page of short bullets scores well regardless of whether the bullets say anything.
- Under three paragraphs it declines to judge and returns a warning rather than guessing from too little text.
Where does this guidance come from?
The scoring rules are Gadex's. The reasoning about why these properties matter draws on the platforms' own published guidance:
- Google Search Central: creating helpful, reliable, people-first content — on self-evident expertise, sourcing, and who the content is for.
- Google Search Central: Article structured data — on author and date fields, and what they are used for.
- OpenAI: bots and crawlers — on how ChatGPT fetches and attributes pages it surfaces.
How we measured this
The counts above come from running the Gadex scorer over the built HTML of every content page on this site, reading each page's main content region only — nav, header and footer links are excluded, because a visitor pastes an article rather than a whole document. Legal boilerplate, the 404 page and generated tool result renderings are excluded as pages where the score would be meaningless. Per that run, the 91 pages counted are the ones a reader could plausibly ask an assistant to summarise.
The scoring thresholds on this page are read from the same module the tool runs, and a test fails the build if the weight documented here stops matching the weight the scorer applies. What none of this can tell you is whether an answer engine will cite a page: citation depends on the model, the prompt, the index and the competing sources, none of which is visible in your markup.
Common questions
Does this push us toward writing for machines?
Partly, and it is worth being honest about that. Shorter paragraphs help retrieval. They also help most readers, which is why the guidance is not in tension with good writing — but a page optimised purely to this metric would read like a listicle, and that is a real cost.
Why 400 characters?
It is roughly where a paragraph stops being a single idea a reader can hold and a model can lift. The number is a heuristic, not a law; 380 and 420 are not meaningfully different.