# HMS Caroline: Agent-Direct Score D (43.4%)

Site: http://www.hmscaroline.co.uk/
Report: https://directindex.org/r/royalnavymuseums.org.uk
Scanned: 2026-11-14 (Provisional: the text without JavaScript could not be measured on this scan, so those points are left out of the total.)
HMS Caroline is hard for agents to use.
An AI assistant may or may not get through to HMS Caroline's website: a plain request was refused and only a full browser got the page. It can't find a menu or price list, so it answers from other sites. It finds a way to book or order directly, through Fever.

## Direct links
- Book: https://cdn.feverup.com/utmkeeper.js (through Fever acting for the business)
- Phone: +44 2890454484 (from OpenStreetMap)
- Address: Queens Road (from OpenStreetMap)
- Prices: 3 prices on the site, the middle one £7.00
- Is this right? https://directindex.org/about?dispute=royalnavymuseums.org.uk#contact

## What assistants answer
The assistants haven't been asked about this business by name yet. In this index they're asked by name about every claimed business; what they answer is shown here, beside the score, never in it.

## What to fix first
- **No structured data for the business.** [no_structured] (+15 points) Add schema.org JSON-LD for the business (TouristAttraction, Museum, TravelAgency or the closest type, with name, address, telephone and openingHoursSpecification). Every assistant reads this block first, and the fix kit below has it filled in. Passes when the home page has schema.org JSON-LD that names the business and its type. Guide: https://directindex.org/guides/structured-data-restaurant
- **No tickets and prices found.** [menu_none] (+7 points) Agents answer 'what does it cost and when?' from marketplaces instead. Add a page with tickets, times and prices as text, and link to it from the homepage. Passes when the home page links a menu or price list as an HTML page on the site. Guide: https://directindex.org/guides/menu-pdf-ai
- **Only a full browser got the page; a plain request was refused.** [blocked_for_bots] (not scored, worth checking) A request from a data centre got TimeoutError: The operation was aborted due to timeout, and a real browser got the page, so the rest was read on the page as the browser showed it. The assistants' own fetchers come from their companies' addresses, and walls like this often let them through, so this does not show that ChatGPT or Claude are refused. Measured, not scored. If an assistant says it can't open the site, ask the host to let ChatGPT-User, Claude-User and Perplexity-User through. Passes when a plain request without a browser gets the page (not scored). Guide: https://directindex.org/guides/blocking-ai-crawlers-without-knowing

## What the site tells visitors (Measured, not scored)
- **3 prices on the landing page, the middle one £7.00.** 

## Fix kit: What to paste

Structured data (JSON-LD). Paste it as one block in the page's head, or in the builder's custom code box. Change anything that's wrong.

```html
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "TouristAttraction",
  "name": "HMS Caroline",
  "url": "http://www.hmscaroline.co.uk/",
  "telephone": "+442890454484",
  "address": {
    "@type": "PostalAddress",
    "streetAddress": "Queens Road"
  },
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 54.6138856,
    "longitude": -5.9025938
  },
  "potentialAction": [
    {
      "@type": "ReserveAction",
      "target": {
        "@type": "EntryPoint",
        "urlTemplate": "https://cdn.feverup.com/utmkeeper.js",
        "actionPlatform": [
          "http://schema.org/DesktopWebPlatform",
          "http://schema.org/MobileWebPlatform"
        ]
      },
      "result": {
        "@type": "Reservation",
        "name": "Reservation"
      }
    }
  ]
}
</script>
```

## Already right
- **robots.txt lets the assistants in.** No rule blocks the main AI user agents.
- **Tickets through Fever on your own domain.** There's no marketplace commission, and the customer stays yours.

## Where it stands
73 of 105 in Belfast tours, attractions and museums. Ahead of 30% of the other sites scanned in this index.

| What the top 10% of the index does | Top 10% | This site |
|---|---|---|
| Take bookings or orders on their own domain | 100% | yes |
| Publish the menu or price list as HTML | 73% | no |
| Let the assistants in (robots.txt) | 100% | yes |
| Structured data with address, phone and hours | 64% | no |
| Have an llms.txt | 36% | no |


Compared with its peers: Sites using Fever 53% (27% A or B, 67 sites); This site 43.4%.

See what an AI agent reads on this site: https://directindex.org/r/royalnavymuseums.org.uk/agent-view

## Businesses like HMS Caroline in Belfast tours, attractions and museums

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in Belfast tours, attractions and museums | 105 | 53% | 29% | 43.4% |

With the two fixes above (No structured data for the business; No tickets and prices found), the score would be about 85%. Against today's scores in Belfast tours, attractions and museums, that would rank about 8th of 105 (it is 73rd today). The others' scores move too, so this is an estimate.

## The direct record
What agents get for HMS Caroline, as JSON: https://directindex.org/api/direct/royalnavymuseums.org.uk
- Book: https://cdn.feverup.com/utmkeeper.js (vendor on own site: Fever; found by the scan of 2026-11-14, not yet tested)
- Order: none on record
- Menu: none on record
- Hours: none on record
- Phone: +442890454484
- Stable links that count: https://directindex.org/go/royalnavymuseums.org.uk/book

## Can an agent transact?
Measured, not scored (not part of the Agent-Direct Score, spec 1.1).
- UCP profile (/.well-known/ucp, Google and Shopify's Universal Commerce Protocol): no
- ACP discovery document (/.well-known/acp.json, OpenAI and Stripe's Agentic Commerce Protocol): no
- MCP server card (/.well-known/mcp/server-card.json): no
- Ordering vendor that takes agent orders (Square, Toast, or a vendor whose terms allow agents): no
- Vendor terms for agents, Fever: Not stated. The terms do not address an agent acting for a person (several bar scraping or data extraction only), could not be read on the date given, or the vendor has not been researched yet.

Only a real browser got this page (a plain fetch got TimeoutError: The operation was aborted due to timeout); Readable and Actionable were measured on the rendered page.

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 13 | 13 (the text without JavaScript: pending) |
| Readable | 0 | 25 |
| Actionable | 10 | 15 |

Scored on what the scan measures for every site, the same way for everyone. The action test and what the assistants answer are shown beside the score, never in it (specification 1.1, 18 November 2026).

### Who can read the site, by kind of agent
| Kind of agent | What the scan saw | In the score |
|---|---|---|
| Search crawlers (OAI-SearchBot, Claude-SearchBot, PerplexityBot) | let in by robots.txt | 10 points, the two rows together |
| Fetchers that read a page for a person (ChatGPT-User, Claude-User, Perplexity-User) | let in by robots.txt | 10 points, the two rows together |
| Training crawlers | let in by robots.txt | not scored |
| Requests under crawler names from Cloudflare's network | refused: GPTBot, ClaudeBot, PerplexityBot | not scored |
| The scanner's own signed request | refused; only a browser got the page | 2 points: the text without JavaScript |

## Agent readiness (Cloudflare)
Not measured for this scan.
- JSON-LD for the business: no

Own this business? Claim it, correct what agents are told, recheck a fix, or hand the list to your assistant: https://directindex.org/r/royalnavymuseums.org.uk/owner
Methodology: https://directindex.org/methodology · Rescan now: https://directindex.org/scan?url=royalnavymuseums.org.uk&force=1
