Agent View
The site as an AI agent gets it, beside the site as a person sees it. What it can read, what it has to cut away, and what it never sees.
0
Skip to ContentReservationsDinnerLunch (Saturdays)Daily Happy Hour SpecialsPro Shop Grab & Go MenuSullivan County Golf ClubABOUT
@ottosliberty[email protected]Foster Supply HospitalityThe DeBruceHemlock NeversinkKenoza HallThe Arnold House
Nothing. The HTML the server sends has no text of its own for a reader to turn into Markdown.
No text: Put the page’s own words in the HTML the server sends, inside <main>. No h1: Give each one h1 that says what the page is.
The figures
5 pages, set against the 169,088 sites with figures and 66 in restaurants.
- Readablehigher is better
- 60%3 of 5 pages
- All 169,088 sitesBetter than 19%66 restaurants sitesBetter than 5%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 23%middle page
- All 169,088 sitesBetter than 12%66 restaurants sitesBetter than 13%
Of the words before script, the share that are the page and not menus, footer and forms.
- Costshown, never scored
- 559tokens
- About 112 a page
To read every page once. A long page that answers well is not worse for it. Tokens are estimated at about 4 characters each.
How its pages spread on Clean
5 pages measured.
Against its rivals
The sites nearest it by what they do, with figures. Close means similar work, not better.
| Readinghigher is better | Costnot scored | ||
|---|---|---|---|
| Site | Readable | Clean | Tokens a page |
| ottosliberty.comThis site, 5 pages | 60% | 23% | 112 |
| thephoeniciansteakhouse.com6 pages | 100% | 74% | 1,034 |
| golaosteria.com57 pages | 96% | 63% | 618 |
| simeonsithaca.com16 pages | 94% | 33% | 397 |
Fourth of 4 on Readable, fourth on Clean.
AI crawler access
What robots.txt says to each, as read on October 25, 2026. 8 of 8 may read the site.
| Crawler | robots.txt says | Used for | The line that decides |
|---|---|---|---|
| GPTBotOpenAI | Allowed | Training models | User-agent: GPTBot / Disallow: /config |
| OAI-SearchBotOpenAI | Not named | ChatGPT search | Falls to User-agent: * |
| ChatGPT-UserOpenAI | Not named | A page a person asks about | Falls to User-agent: * |
| ClaudeBotAnthropic | Allowed | Training models | User-agent: ClaudeBot / Disallow: /config |
| Claude-SearchBotAnthropic | Not named | Claude’s search | Falls to User-agent: * |
| PerplexityBotPerplexity | Not named | Perplexity search | Falls to User-agent: * |
| Google-ExtendedGoogle | Allowed | Training Gemini | User-agent: Google-Extended / Disallow: /config |
| bingbotMicrosoft | Not named | Bing and Copilot | Falls to User-agent: * |
Every AI crawler mttr checks may read it. Not named means the rules for every crawler apply.
Every page
Worst first. Each opens in Agent View at the top.
5 pages of 5 lose something. Pick a loss to see what to do about it.Open the action plan
| What an agent getshigher is better | Signals | Costnot scored | ||||
|---|---|---|---|---|---|---|
| Page | Words | Clean | Readable | Main heading | Tokens | What it loses |
| /cart | 0 | 0% | No | None | 0 | No text and 1 more |
| / | 31 | 23% | No | None | 86 | Thin and 1 more |
| /reservations | 18 | 14% | Yes | None | 45 | No h1 |
| /home | 31 | 23% | Yes | None | 86 | No h1 |
| /about | 215 | 66% | Yes | None | 342 | No h1 |
Show where it stands
A card, a badge and a line, each with the figures.
A badge for the site
<a href="https://mttr.si/agent-view/ottosliberty.com"><img src="https://mttr.si/agent-view/ottosliberty.com/badge.svg" alt="Agent View: 60% readable, 23% clean" height="20"></a>
The figures in one line
ottosliberty.com in Agent View: 60% of pages readable, better than 5% of restaurants sites; 23% clean; 559 tokens to read all 5 pages. mttr.si/agent-view/ottosliberty.com
What to do next
Fix the pages, let an agent do it, and read the site again to see the figures move.
Fix what agents miss
- Give 5 pages a main headingClearer
- Render the rest of 1 page on the serverReadable
- Give 1 page text of their ownReadable
Connect your agent
Claude Code, Codex or Cursor reads the site’s fixes over MCP, fixes a page in your code, has mttr read it again, and checks the fix landed.
https://mttr.si/mcpSet up an agent
Claim the site
Prove it is yours with a DNS record or a file. Your agent can then reach its reads and jobs, and set each change to wait for your approval.
Claim the siteDrawn from the HTML mttr fetched on its read of October 25, 2026, not a screenshot, and only from the 5 pages read. An assistant’s own reader may differ. Tokens are estimated at about 4 characters each. A site an agent reads well is not a site an assistant cites.