# scent: Agent-Direct Score D (47.7%)

Site: https://www.cosmo-hotel.de/en/restaurant
Report: https://directindex.org/r/cosmo-hotel.de
Scanned: 2026-10-14 (provisional: the action test and the assistant citation check pending)
scent is hard for agents to use.

## What to fix first
- **No structured data for the business.** Add schema.org JSON-LD for the business (Restaurant, LocalBusiness or the closest type) with name, address, telephone and openingHoursSpecification, plus servesCuisine and acceptsReservations for a restaurant. It is the one block every assistant reads first. Guide: https://directindex.org/guides/structured-data-restaurant
- **No menu or price list found.** Agents answer 'what do they offer' from marketplaces instead. Add a menu or price list page and link it from the homepage. Guide: https://directindex.org/guides/menu-pdf-ai
- **Booking through an unrecognised third party.** Check that the provider keeps you as the merchant of record. Guide: https://directindex.org/guides/book-direct-on-your-own-website
- **No llms.txt.** 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

## Already right
- **robots.txt lets AI crawlers in.** There is no robots.txt, which allows everything.
- **AI crawlers get the page.** GPTBot, ClaudeBot and PerplexityBot all received a normal response.

## Where it stands
Rank 1455 of 3017 in Berlin (top 48%).

| What the top tenth does | Top 10% | This site |
|---|---|---|
| Take bookings or orders on their own domain | 78% | no |
| Publish the menu or price list as HTML | 79% | no |
| Let AI crawlers in (no edge block, no robots.txt block) | 83% | yes |
| Structured data with address, phone and hours | 43% | no |
| Have an llms.txt | 22% | no |

Nearest places with a similar menu: Erdinger am Gendarmenmarkt (D, 620 m, https://directindex.org/r/erdingerberlin.de); Baret (F, 645 m, https://directindex.org/r/baret.berlin); Zur Gerichtslaube (F, 686 m, https://directindex.org/r/gerichtslaube.de); Tim Raue (D, 846 m, https://directindex.org/r/tim-raue.com); Nobelhart & Schmutzig (B, 1013 m, https://directindex.org/r/nobelhartundschmutzig.com); W66 (D, 1025 m, https://directindex.org/r/w66berlin.com); Nante-Eck (A, 1054 m, https://directindex.org/r/nante-eck.de); Zur Letzten Instanz (C, 1057 m, https://directindex.org/r/zurletzteninstanz.com); Ursprung (D, 1129 m, https://directindex.org/r/ursprung-berlin.com); Treffpunkt Berlin (C, 1130 m, https://directindex.org/r/treffpunktberlin.com).

## What assistants answer
Not asked yet. Assistants are asked about the top-ranked and claimed businesses in each city index.

## Score breakdown
| Component | Points | Available |
|---|---|---|
| reachable | 25 | 25 |
| readable | 0 | 25 |
| actionable | 6 | 15 (action_test pending) |
| cited | 0 | 0 (probes pending) |

## Agent readiness (Cloudflare criteria)
Level 0 of 5: Not Ready. Cloudflare's report: https://isitagentready.com/cosmo-hotel.de
- 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: no (how: https://isitagentready.com/.well-known/agent-skills/ai-rules/SKILL.md)
- 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: no

Methodology: https://directindex.org/methodology · Rescan: https://directindex.org/scan?url=cosmo-hotel.de&force=1