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 8 points, a warning earns half, a fail earns none.
| Result | How it is decided |
|---|---|
| Pass | Two or more definition-shaped phrases. |
| Warn | Exactly one. |
| Fail | None. |
Why does this check exist?
A definition is the most reusable sentence shape there is. "GEO is the practice of..." can be lifted into an answer about GEO with no rewriting, which makes it disproportionately likely to be the sentence that gets quoted.
Defining terms also disambiguates the page. A model deciding whether this page is about generative engine optimisation or geography resolves that from an explicit definition far more reliably than from context.
The threshold is two because one definition is often just a topic sentence. Two suggests the page is actually explaining its vocabulary.
How do you fix it?
- Define each significant term once, in plain language, near where it first appears.
- Use the copula. "GEO is the practice of making content easy for answer engines to quote" is extractable; "GEO — the new frontier of search" is not.
- Do not pad. Adding definitions of terms your audience already knows makes the page worse for readers and does not make it more citable.
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/: 62 pass, 17 carry a warning, and 12 fail. Per that same run, 32 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 counts phrase shapes, not meaning. "This is a good question" matches. That is the cost of pattern matching without comprehension.
- It cannot tell a definition of your subject from a definition of something incidental.
- Counting means a page can pass by repeating a shape rather than by explaining anything. Read the page, not the number.
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
Our audience are experts. Do we still need definitions?
For readers, often not. For retrieval, a definition is still the sentence most likely to be quoted, and expert pages routinely define terms of art precisely because precision matters. Define what is contested or ambiguous in your field rather than what is elementary.
Does a glossary section satisfy this?
It satisfies the check easily. Whether it helps depends on placement — a definition beside its first use serves a reader better than one filed at the bottom.