Skip to content
Is Agentic

snowsure.ai

Strong technical baseline

97/ 100

Technical readiness score

What should the prompt cover?

7 findings · 5 selected

Warnings (7)

How the score adds up

44 checks

Starting an observed agent task

This run is collected separately from the technical score and will appear here as the agent moves through the public site.

Starting the agent…

Critical access needs attention

These checks describe whether an ordinary agent can enter, read, and operate the public site.

  • Agents can reach the site

    Crawler access, bot defenses, and explicit agent policy.

    3 / 3 passed

  • Core content is available

    Useful content remains accessible without a fragile browser-only path.

    1 / 2 passed

  • Navigation fails safely

    Redirects and missing pages give agents a recoverable path.

    1 / 2 passed

  • Controls are understandable

    Forms and interactive controls expose usable names and structure.

    2 / 2 passed

Advertised capabilities are technically strong

Optional surfaces appear only when the scan finds positive evidence that the site offers them.

Public website

Strong

88%

14 of 19 mature checks passed

API

Strong

98%

15 of 16 mature checks passed

Authentication

Strong

100%

3 of 3 mature checks passed

MCP

Strong

97%

5 of 6 mature checks passed

Fix these gaps first

Critical access gaps come first, followed by gaps in capabilities the site advertises.

  1. 01

    Content without JavaScript

    Server-side render your homepage so AI crawlers see meaningful content without JavaScript. Ensure an H1 and 500+ chars of text in raw HTML.

    Critical access
  2. 02

    Agent-friendly 404s

    Return a real HTTP 404 (or 410) status for nonexistent paths - never a 200 with your app shell, which makes agents believe every path exists. For full credit, give the 404 response a short markdown body pointing agents at your sitemap, llms.txt, or docs index. Verify with `curl -s -o /dev/null -w "%{http_code}" https://yourdomain.com/some-path-that-does-not-exist` - it must print 404.

    Critical access
  3. 03

    Content efficiency

    Reduce markup overhead so readable text is at least 5% of your HTML. Strip unused inline scripts/styles, server-render content instead of shipping large JSON hydration blobs, and keep wrapper nesting shallow.

    Advertised capabilities
  4. 04

    Agent instruction / when-to-use

    Tell agents when to reach for you: add a 'when to use this' section to your llms.txt (or a dedicated agent-instructions file) that names your best-fit use cases and how an agent should call you. Be specific about the jobs you are right for - generic marketing copy does not read as guidance.

    Advertised capabilities
  5. 05

    Developer resource discoverability

    Make your developer resources (API docs, OpenAPI spec, auth docs, webhooks, MCP server) discoverable by name. Publish them at predictable URLs, list them in llms.txt, and include your product name in page titles and headings so search engines surface them for name-based queries.

    Advertised capabilities

Audit the checks behind the score

Applicable evidence is grouped by how it contributes to this preview model. Bonus checks appear only when they add points.

Essential12 of 14 passed · 73.3 / 80 points
  • Content without JavaScriptPartial (33%)
  • Not blocked by bot detectionPassed
  • robots.txt agent-user policyPassed
  • Redirect hygienePassed
  • Content behind authPassed
  • OpenAPI spec publishedPassed
  • Agent crawler reachabilityPassed
  • OAuth 2.0 supportPassed
  • Scoped permissionsPassed
  • JSON error responsesPassed
  • MCP resources exposedPassed
  • Agent-friendly 404sPartial (50%)
  • MCP App view reachablePassed
  • MCP App view CSPPassed
Recommended25 of 30 passed · 18.9 / 20 points
  • Developer resource discoverabilityPartial (67%)
  • Brand name discoverabilityPassed
  • robots.txt AI crawler policyPassed
  • Sitemap existsPassed
  • Content efficiencyPartial (50%)
  • JSON-LD structured dataPassed
  • Public API/docs linked from homepagePassed
  • Agent instruction / when-to-usePartial (67%)
  • Metadata completenessPassed
  • Organization schema completenessPassed
  • Trust anchor pagesPassed
  • Page token budgetPassed
  • Code fence validityPassed
  • Developer portalPassed
  • Public API with reachable endpointsPassed
  • Agent onboarding frictionPassed
  • MCP server / manifestPassed
  • Rate limit response headersPassed
  • Idempotency-Key supportPassed
  • REST typed error modelPassed
  • REST versioning / deprecation policyPassed
  • REST pagination patternPassed
  • REST async-job patternPassed
  • CLI tool availablePassed
  • Multi-language SDK packagesPartial (67%)
  • REST response schema coveragePassed
  • MCP Apps supportPassed
  • API schema complexity analysisPassed
  • Function calling compatibilityPassed
  • MCP resource qualityPartial (83%)
Bonus signals54 positive · +5 points
  • ARD / ai-catalogPassed
  • ARD entry validityPassed
  • ARD trust manifestPassed
  • Wikipedia / Wikidata entity presencePartial (50%)
  • Listed in MCP registriesPassed
  • NPM/PyPI SDK packagePassed
  • Agent platform configsPassed
  • Registry brandingPassed
  • ChatGPT app listedPassed
  • Agent discovery filePassed
  • A2A / agent-cardPassed
  • NLWeb Schema FeedsPassed
  • MCP well-known discoveryPassed
  • Agent mode viewPassed
  • HTTP Link headers (RFC 8288)Passed
  • Markdown URL fallbackPartial (50%)
  • Modular llms.txt per product areaPassed
  • Sitemap freshness (lastmod)Passed
  • llms.txt existsPassed
  • llms.txt formattingPartial (50%)
  • JSON-LD entity linking (sameAs)Passed
  • Speakable content markupPassed
  • Schema type breadthPartial (50%)
  • llms.txt links resolvePassed
  • Markdown alternate linkPassed
  • API catalog (RFC 9727)Passed
  • Markdown agent docsPassed
  • Markdown content negotiation (acceptmarkdown.com)Passed
  • MCP tool descriptionsPassed
  • MCP parameter schemasPassed
  • MCP server identityPassed
  • MCP tool listingPartial (83%)
  • MCP tool namingPassed
  • MCP auth mechanismPassed
  • Web Bot Auth directoryPassed
  • OAuth Protected Resource metadata (RFC 9728)Passed
  • auth.md existsPassed
  • auth.md structurePassed
  • auth.md walkthrough simulationPassed
  • Agent auth discovery metadataPassed
  • Agent auth WWW-Authenticate hintPassed
  • agent_auth endpoints reachablePassed
  • MCP error handlingPassed
  • MCP modern transportPassed
  • WebMCP supportPassed
  • MCP tool annotationsPassed
  • MCP server-card.jsonPassed
  • Product + docs MCP coveragePassed
  • REST batch / bulk endpointPassed
  • Native interactive controlsPassed
  • Accessible names on controlsPassed
  • Accessibility-tree injection safety (bonus)Passed
  • A2UI / generative UI supportPassed
  • MCP Apps UI qualityPassed

Inspect the underlying audit

The complete Ora audit uses evidence from the scan on . After applying changes, run another scan from the homepage to refresh these recommendations.

Score alerts

A weekly report with ranking changes, new agent feedback, and score alerts for snowsure.ai.

Source: Ora API

Snapshot 2026-08-20T12-14-56-548Z