# Old Town Italy: Agent-Direct Score B (81.5%)

Site: https://oldtown.co.za/restaurant/#CONSTANTIA
Report: https://directindex.org/r/oldtown.co.za
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.)
Old Town Italy is mostly ready for agents.
An AI assistant can open the website of Old Town Italy. What Old Town Italy offers is in a PDF or an image, which assistants read poorly. It finds a way to book or order directly on the site.

## Direct links
- Book directly: https://oldtown.co.za/reservations/ (on the business's own site)
- Menu: https://oldtown.co.za/wp-content/uploads/2026/05/OTI_Breakfast-Menu_Apr26_Web.pdf
- Phone: +27 21 569 3784

## What to fix first

- **Structured data is incomplete.** (+6 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
- **No llms.txt.** (no points, still worth doing) Optional today, cheap to add: a short text file describing the business for language models. Guide: https://directindex.org/guides/llms-txt-for-a-business

## 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": "Restaurant",
  "name": "Old Town Italy",
  "url": "https://oldtown.co.za/restaurant/#CONSTANTIA",
  "telephone": "+27 21 569 3784",
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": -34.0247045,
    "longitude": 18.4297862
  },
  "openingHours": "Mo-Su 09:00-22:00",
  "openingHoursSpecification": [
    {
      "@type": "OpeningHoursSpecification",
      "dayOfWeek": [],
      "opens": "09:00",
      "closes": "22:00"
    }
  ],
  "servesCuisine": [
    "italian"
  ],
  "acceptsReservations": "https://oldtown.co.za/reservations/",
  "hasMenu": "https://oldtown.co.za/wp-content/uploads/2026/05/OTI_Breakfast-Menu_Apr26_Web.pdf",
  "potentialAction": [
    {
      "@type": "ReserveAction",
      "target": {
        "@type": "EntryPoint",
        "urlTemplate": "https://oldtown.co.za/reservations/",
        "actionPlatform": [
          "http://schema.org/DesktopWebPlatform",
          "http://schema.org/MobileWebPlatform"
        ]
      },
      "result": {
        "@type": "Reservation",
        "name": "Reservation"
      }
    }
  ]
}
</script>
```

llms.txt. Save as /llms.txt at the root of the site.

```
# Old Town Italy

> restaurant (italian) in Cape Town. Phone +27 21 569 3784.

## Book or order directly

- Book: https://oldtown.co.za/reservations/ (on the business's own site)
- Menu: https://oldtown.co.za/wp-content/uploads/2026/05/OTI_Breakfast-Menu_Apr26_Web.pdf

## Opening hours

Mo-Su 09:00-22:00

## About

- Website: https://oldtown.co.za/restaurant/#CONSTANTIA
- This file follows llms.txt (https://llmstxt.org): a short plain-text description for language models.
```

## Already right
- **robots.txt lets AI crawlers in.** No rule blocks the key AI user agents.
- **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 on your own site.** Agents can book without a marketplace in the loop.

## Where it stands
15 of 134 in Cape Town. Top 11% 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 | 86% | no |
| Let AI crawlers in (no edge block, no robots.txt block) | 86% | yes |
| Structured data with address, phone and hours | 36% | no |
| Have an llms.txt | 43% | no |

Nearest places in the index: Jonkershuis Eatery (B, 1192 m, https://directindex.org/r/jonkershuisconstantia.co.za); Simon's Restaurant (C, 1335 m, https://directindex.org/r/simons.co.za); Constantia Glen Restaurant (B, 2165 m, https://directindex.org/r/constantiaglen.com); Beyond Restaurant (D, 2284 m, https://directindex.org/r/buitenverwachting.com); La Colombe (F, 2664 m, https://directindex.org/r/lacolombe.restaurant); Four & Twenty Cafe & Pantry (C, 3671 m, https://directindex.org/r/fourandtwentycafe.co.za).

## 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.

Asked 12 everyday questions about Cape Town, the assistants named 65 places; Old Town Italy was not among them. See who was named: https://directindex.org/city/cape-town/recommended


Against its peers: Sites built with WordPress 58% (30% A or B, 68857 sites); This site 81.5%.

See what an AI agent reads on this site: https://directindex.org/r/oldtown.co.za/agent-view

## Businesses like Old Town Italy in Cape Town

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in Cape Town | 134 | 53% | 23% | 81.5% |
| Sites built with WordPress in Cape Town | 68 | 63% | 28% | 81.5% |

The best of the sites built with WordPress in Cape Town: Ferrymans Tavern (A 100%, https://directindex.org/r/ferrymans.co.za); Woodlands Eatery (A 94.9%, https://directindex.org/r/thewoodlandseatery.com); Ramenhead (A 89.2%, https://directindex.org/r/ramenhead.co.za); Catch 22 (A 86.2%, https://directindex.org/r/catch22restaurant.co.za); Mitchell's Scottish Ale House Victoria & Alfred Waterfront (A 86.2%, https://directindex.org/r/mitchellsalehouse.co.za).

With the two fixes above (Structured data is incomplete; Menu or price list is a PDF) the score would be about 95.4%: 3rd of 134 in Cape Town, up from 15th.

## The direct record
What agents get for Old Town Italy, as JSON: https://directindex.org/api/direct/oldtown.co.za
- Book: https://oldtown.co.za/reservations/ (own site; found by the scan of 2026-10-17, not yet tested)
- Order: none on record
- Menu: https://oldtown.co.za/wp-content/uploads/2026/05/OTI_Breakfast-Menu_Apr26_Web.pdf (pdf; from the scan)
- Hours: Mo-Su 09:00-22:00 (open now) (from OpenStreetMap)
- Phone: +27 21 569 3784
- Stable links that count: https://directindex.org/go/oldtown.co.za/book, https://directindex.org/go/oldtown.co.za/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

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 25 | 25 |
| Readable | 13 | 25 |
| Actionable | 15 | 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/oldtown.co.za
- 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: no (how: https://isitagentready.com/.well-known/agent-skills/llms-txt/SKILL.md)
- 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/oldtown.co.za/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/oldtown.co.za/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=oldtown.co.za&force=1