The rubric,
in full.
One number, published in the open. Every check, every weight, every penalty — because a legibility score nobody can audit is a marketing claim wearing a number.
The version is stamped on every scan. A score produced under one version is never compared with a score produced under another.
How the number is built
Catalogue checks contribute 80%, schema markup 20%. Blocked AI crawlers are then subtracted — 6 points each, capped at 30. Nothing is rounded, curved or tuned to make a demo look better.
(80% × catalogue) + (20% × schema) − (6 × blocked crawlers, max 30)
Catalogue checks
Weights sum to 100 before the blend. Measured per product, averaged across the catalogue.
- Description depth16 / 95
Under ~180 characters there is nothing for an agent to extract facts from.
- Structured attributes15 / 95
Material, dimensions, composition. The fields agents filter and compare on.
- SKU coverage12 / 95
Every variant needs a stable identifier or an agent cannot reference what it buys.
- Product type set12 / 95
Blank type means your product joins no comparison set at all.
- Tag richness10 / 95
Three or more per product. How use-case and occasion queries find you.
- Shipping weight9 / 95
No weight means no delivery estimate - you drop out of speed-filtered results.
- Imagery present8 / 95
Multimodal agents read images. No image is a hard skip on visual surfaces.
- Real variant options8 / 95
Default Title tells an agent nothing about size, colour or configuration.
- Vendor named5 / 95
Brand attribution. Feeds brand queries and Merchant Center matching.
Schema markup
Structured data on the product page, worth 20% of the composite.
- JSON-LD Product block40
- Offer with a price20
- Availability stated20
- Shipping details20
Crawler penalty
Every AI agent your robots.txt refuses costs 6 points of the composite, to a maximum of 30. These are the ten agents checked.
- GPTBot
- OAI-SearchBot
- ChatGPT-User
- ClaudeBot
- anthropic-ai
- PerplexityBot
- Google-Extended
- Applebot-Extended
- Bytespider
- CCBot
What the score means
80 and above. Agents can read, compare and cite the catalogue.
50 to 79. Some products surface; the rest are guesswork.
Under 50. Agents cannot reliably answer questions about the catalogue.
What this score is not
- It is not a ranking. It measures whether a machine can read your catalogue, not where you place in anyone's results.
- It is not a promise or a refund term. It is a measurement — what a machine can read of your catalogue today, traceable to the exact checks and weights on this page.
- It is not final. The rubric is audited quarterly against a live cohort, and when a check is found to measure something other than what it claims, it is corrected and the version moves.
