Make answers quotable

What does this finding mean?

The report identifies this check as schema-direct-answers in Structured data. The category carries up to 16 of the 100 rubric points. This is a category weight, not an automatic deduction for this finding. Read the scan detail for the measured state, overlapping signals and any score cap.

The scanner recommends 40 to 300 characters per acceptedAnswer as a local heuristic. This is not a vendor requirement. State the answer first, keep any necessary qualification and match the visible FAQ exactly.

Why does this matter for AI retrieval?

Valid markup labels the entities and content already visible on a page. Parsers can use those explicit relationships. No schema type guarantees selection by ChatGPT, Claude, Perplexity or Gemini, and this score is our rubric rather than a vendor ranking formula.

How do I check and resolve it?

1. Choose an actual question the page answers. Write a complete answer directly below it in visible HTML.
2. For a page with visible FAQs, mirror each Question and acceptedAnswer in FAQPage markup. Do not add hidden questions or promotional text.
3. Keep each answer factual and understandable without the surrounding article. Update the HTML and JSON-LD from the same content source.

Adapt the example to the reported issue and the actual route. Placeholder names, URLs and dates must be replaced with facts from your site.

Copy code

<h2>Can I block training and keep search access?</h2>
<p>Yes. Give GPTBot and OAI-SearchBot separate robots.txt groups.</p>
<script type="application/ld+json">
{"@context":"https://schema.org","@type":"FAQPage",
 "mainEntity":[{"@type":"Question",
 "name":"Can I block training and keep search access?",
 "acceptedAnswer":{"@type":"Answer",
 "text":"Yes. Give GPTBot and OAI-SearchBot separate robots.txt groups."}}]}
</script>

Verify the result

Compare every schema question and answer with the visible FAQ. Parse the JSON and rescan the direct-answers principle. FAQ markup alone does not establish rich-result eligibility.

Open the related tool or technical guide, then run a new scan of the affected URL. Keep unknown checks marked unknown until you have a complete response.

Copy a prompt for your coding agent

Paste this into Codex, Claude Code or Cursor from your own repository. Include the scan's exact URL and detail so the agent can verify the observation.

Copy prompt for coding agent

Investigate the scanner finding "Make answers quotable" (schema-direct-answers) in this repository.
Observation: The scanner found FAQ answers that need clearer standalone wording or a length review.
Required change: The scanner recommends 40 to 300 characters per acceptedAnswer as a local heuristic. This is not a vendor requirement. State the answer first, keep any necessary qualification and match the visible FAQ exactly.
Inspect the existing route, shared layouts and configuration first. Confirm the finding against the actual response before editing. Preserve intentional access restrictions, existing content and unrelated changes. Use only factual identity and date values. Make the smallest appropriate fix, verify the deployed HTML or resource response and run the relevant project checks. Explain any measurement that remains unknown. Do not promise search rankings or AI citations.
Reference: https://letthebots.in/fixes/schema-direct-answers/