# Captain Baxter: Agent-Direct Score B (70.5%)

Site: https://www.captainbaxter.com.au/
Report: https://directindex.org/r/baxterstkilda.com.au
Scanned: 2026-10-17 (Provisional: the action test and the assistant citation check still to come; the hatched part of the bar is not measured yet.)
Captain Baxter is mostly ready for agents.
Some AI assistants are turned away by the website of Captain Baxter. What Captain Baxter offers is in a PDF or an image, which assistants read poorly. It finds a way to book or order directly, through SevenRooms.

## Direct links
- Book directly: https://www.sevenrooms.com/explore/baxter/reservations/create/search/ (through sevenrooms acting for the business)
- Menu: https://baxterstkilda.com.au/wp-content/uploads/downloads/Baxter_Menu.pdf

## What to fix first
- **Structured data is incomplete.** (+7 points) Missing: address, telephone, opening hours. Guide: https://directindex.org/guides/structured-data-restaurant
- **Menu or price list is a PDF.** (+3 points) Most agents skip PDFs or read them badly. Publish it as HTML, keep the PDF as a download. Guide: https://directindex.org/guides/menu-pdf-ai
- **robots.txt blocks GPTBot.** (+1.2 points) These are the crawlers behind ChatGPT, Claude, Perplexity and Google's AI features. Remove the Disallow lines for them, or add explicit Allow rules. Guide: https://directindex.org/guides/robots-txt-for-ai-agents

## Fix kit: What to paste

Structured data (JSON-LD). One block in the page's head, or in the builder's custom-code slot. Replace anything that is wrong.

```html
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "BarOrPub",
  "name": "Captain Baxter",
  "url": "https://www.captainbaxter.com.au/",
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": -37.865562,
    "longitude": 144.972422
  },
  "acceptsReservations": "https://www.sevenrooms.com/explore/baxter/reservations/create/search/",
  "hasMenu": "https://baxterstkilda.com.au/wp-content/uploads/downloads/Baxter_Menu.pdf",
  "potentialAction": [
    {
      "@type": "ReserveAction",
      "target": {
        "@type": "EntryPoint",
        "urlTemplate": "https://www.sevenrooms.com/explore/baxter/reservations/create/search/",
        "actionPlatform": [
          "http://schema.org/DesktopWebPlatform",
          "http://schema.org/MobileWebPlatform"
        ]
      },
      "result": {
        "@type": "Reservation",
        "name": "Reservation"
      }
    }
  ]
}
</script>
```

robots.txt. Add these lines to /robots.txt and delete any Disallow rule that names these crawlers.

```
# Let AI assistants read the site: they send people to you; a marketplace keeps them.
# Remove any Disallow lines for these names elsewhere in this file.
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Perplexity-User
Allow: /
```

## Already right
- **AI crawlers get the page.** GPTBot, ClaudeBot and PerplexityBot all received a normal response.
- **Structured data present (Organization).** but without address, phone or hours
- **Booking through sevenrooms on your own domain.** No marketplace commission, and the guest stays yours.
- **SevenRooms works with agents through its partners.** SevenRooms' terms (17 April 2026) bar any robot, spider, scraper or other automated means except bona fide search engines; Google names SevenRooms as an AI Mode booking partner. Read 2026-10-15: https://sevenrooms.com/terms-of-service/. An assistant that is not a partner may not finish the step there; a direct path on your own domain works for all of them.

## Where it stands
307 of 911 in Melbourne cafes and bars. Top 34% of the sites scanned in this index.

| What the top tenth 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 | 95% | no |
| Let AI crawlers in (no edge block, no robots.txt block) | 97% | no |
| Structured data with address, phone and hours | 33% | no |
| Have an llms.txt | 17% | yes |

Nearest places in the index: Beachcomber (A, 93 m, https://directindex.org/r/beachcombercafe.com.au); Theatre Works Café (D, 347 m, https://directindex.org/r/theatreworks.org.au); Prince of Wales Hotel (C, 408 m, https://directindex.org/r/theprince.com.au); Veludo Bar (C, 810 m, https://directindex.org/r/bankofmelbourne.com.au); Frankie's Top Shop (D, 861 m, https://directindex.org/r/frankiestopshop.com.au); Post Office Club Hotel (A, 1207 m, https://directindex.org/r/postofficeclubhotel.com.au); Grosvenor Hotel (A, 1740 m, https://directindex.org/r/grosvenorhotel.au); Holy Grail (A, 2112 m, https://directindex.org/r/gcbg.com.au); Union Hotel (C, 2163 m, https://directindex.org/r/unionhotelwindsor.com.au); Sandbar Beach Cafe (C, 2257 m, https://directindex.org/r/sandbarbeachcafe.au).

## What assistants answer
Not asked yet. Assistants are asked about the top-ranked businesses in each city index, and about every claimed business the moment it is claimed; claim this page to be included.

Against its peers: Sites built with WordPress 59% (32% A or B, 54721 sites); Sites using SevenRooms 70% (52% A or B, 1012 sites); This site 70.5%.

See what an AI agent reads on this site: https://directindex.org/r/baxterstkilda.com.au/agent-view

## Businesses like Captain Baxter in Melbourne cafes and bars

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in Melbourne cafes and bars | 911 | 56% | 34% | 70.5% |
| Sites built with WordPress in Melbourne cafes and bars | 279 | 64% | 42% | 70.5% |
| Sites using SevenRooms in Melbourne cafes and bars | 49 | 70% | 57% | 70.5% |
| Sites built with WordPress and using SevenRooms in Melbourne cafes and bars | 28 | 73% | 64% | 70.5% |

The best of the sites built with WordPress and using SevenRooms in Melbourne cafes and bars: Imperial Hotel (A 86.2%, https://directindex.org/r/bourkestreetimperial.com); Station Hotel (A 86.2%, https://directindex.org/r/thestationhotel.com.au); The Prince Alfred (A 86.2%, https://directindex.org/r/princealfredhotel.com.au); Duke of Wellington Hotel (B 78.5%, https://directindex.org/r/dukeofwellington.com.au); Fairfield Boathouse (B 78.5%, https://directindex.org/r/fairfieldboathouse.com).

With the three fixes above (Structured data is incomplete; Menu or price list is a PDF; robots.txt blocks GPTBot) the score would be about 87.7%: 91st of 911 in Melbourne cafes and bars, up from 307th.

## The direct record
What agents get for Captain Baxter, as JSON: https://directindex.org/api/direct/baxterstkilda.com.au
- Book: https://www.sevenrooms.com/explore/baxter/reservations/create/search/ (vendor on own site: SevenRooms; found by the scan of 2026-10-17, not yet tested)
- Order: none on record
- Menu: https://baxterstkilda.com.au/wp-content/uploads/downloads/Baxter_Menu.pdf (pdf; from the scan)
- Hours: none on record
- Phone: none on record
- Stable links that count: https://directindex.org/go/baxterstkilda.com.au/book, https://directindex.org/go/baxterstkilda.com.au/menu

## Can an agent transact?
Measured, not scored (the score stays at spec v1.0).
- 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, SevenRooms: Through partners. SevenRooms' terms (17 April 2026) bar any robot, spider, scraper or other automated means except bona fide search engines; Google names SevenRooms as an AI Mode booking partner. Read 2026-10-15: https://sevenrooms.com/terms-of-service/

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 23.8 | 25 |
| Readable | 12 | 25 |
| Actionable | 10 | 15 (the action test: pending) |
| Cited | 0 | 0 (the assistant citation check: pending) |

## Agent readiness (Cloudflare)
Level 1 of 5, Basic Web Presence. Cloudflare's report: https://isitagentready.com/baxterstkilda.com.au
- Link headers on the homepage: no (how: https://isitagentready.com/.well-known/agent-skills/link-headers/SKILL.md)
- sitemap.xml: yes
- AI bot rules in robots.txt: yes
- Content Signals in robots.txt: no (how: https://isitagentready.com/.well-known/agent-skills/content-signals/SKILL.md)
- Markdown on Accept: text/markdown: no (how: https://isitagentready.com/.well-known/agent-skills/markdown-negotiation/SKILL.md)
- llms.txt: yes
- API catalog (RFC 9727): no (how: https://isitagentready.com/.well-known/agent-skills/api-catalog/SKILL.md)
- MCP server card: no (how: https://isitagentready.com/.well-known/agent-skills/mcp-server-card/SKILL.md)
- A2A agent card: no (how: https://isitagentready.com/.well-known/agent-skills/a2a-agent-card/SKILL.md)
- Agent Skills index: no (how: https://isitagentready.com/.well-known/agent-skills/agent-skills/SKILL.md)
- OAuth or OIDC discovery: no (how: https://isitagentready.com/.well-known/agent-skills/oauth-discovery/SKILL.md)
- OAuth protected resource metadata: no (how: https://isitagentready.com/.well-known/agent-skills/oauth-protected-resource/SKILL.md)
- auth.md: no (how: https://isitagentready.com/.well-known/agent-skills/auth-md/SKILL.md)
- Web Bot Auth key directory: no (how: https://isitagentready.com/.well-known/agent-skills/web-bot-auth/SKILL.md)
- ARD capability manifest: no (how: https://isitagentready.com/.well-known/agent-skills/ard/SKILL.md)
- DNS-AID records: no (how: https://isitagentready.com/.well-known/agent-skills/dns-aid/SKILL.md)
- WebMCP tools on the page: no (how: https://isitagentready.com/.well-known/agent-skills/webmcp/SKILL.md)
- JSON-LD for the business: yes

Keep watching this business (https://directindex.org/r/baxterstkilda.com.au/plan): the assistants asked again every month, with what changed; 2 EUR a month or 19 EUR a year.
Deep report: https://directindex.org/r/baxterstkilda.com.au/deep. Ten questions the way people ask, each assistant's full answer, the eight nearest similar places, the fix plan and a PDF: 5 EUR, one-off. Reading and scanning stay free; these few euros pay for the questions sent to the assistants and for the servers.
Methodology: https://directindex.org/methodology · Rescan now: https://directindex.org/scan?url=baxterstkilda.com.au&force=1