--- title: "Intercom agent readiness score: 85/100 · Agentrail" description: "The website’s strongest area is agent discovery, with checks passed for brand name discoverability and robots.txt AI crawler policy, but ARD discovery and Idempotency-Key support are missing." canonical: "https://www.agentrail.co/agent-readiness/intercom.com" --- Full report ## See what each check found, and how to fix it. Evidence, step-by-step fixes and your score over time, for your own site. [Get started →](https://app.agentrail.co/login?utm%5Fsource=agentrail.co&utm%5Fmedium=website&utm%5Fcampaign=agent-readiness%2Fintercom.com&utm%5Fcontent=company-report) Free to start. No card. Usability 18 to fix - Web Bot Auth directoryEmergingHow to fix → - auth.md existsRequiredHow to fix → - auth.md structureRecommendedHow to fix → - Agent auth discovery metadataRecommendedHow to fix → Fixes unlock with the full report Where the score comes from 77 of 90 points How intercom.com scores on each of the four questions agents ask. Discovery18/20 Access26/30 Usability33/40 Paymentsnot scored yet Strongest ### Discovery ARD discovery and Wikipedia / Wikidata entity presence are missing. 18/20 Most to gain ### Usability auth.md exists, auth.md structure, and 13 more are missing. 33/40 Most to gain ### Access Content without JavaScript, Agent discovery file, and 7 more are missing. 26/30 Not scored yet ### Payments ( bonus ) 6 checks partly met. Counts when scoring opens. — Agent path ## How an agent moved through the site We asked an agent a question about intercom.comand recorded every request it made. **I**intercom.comAnsweredRan Nov 8, 2026 Question I want to start using Intercom (intercom.com). Find its setup and getting-started guide. 7 Steps 35s Duration 7 Pages opened 2 Failed 2 of 2 addresses the agent typed itself didn’t load. Every link it followed loaded. 1. 1intercom.com /Named in the question _→_ **Read** 2. 2intercom.com /Typed by the agent _→_ **Didn’t load** 3. 3intercom.com /Typed by the agent _→_ **Didn’t load · 301** 4. 4/helpA link on a page it read _→_ **Read** 5. 5/help/en/collections/1865264-getting-startedA link on a page it read _→_ **Read** 6. 6/help/en/collections/9959325-quick-start-guidesA link on a page it read _→_ **Read** 7. 7/help/en/collections/2094824-setting-up-your-workspaceA link on a page it read _→_ **Read** 7/7 steps StepsHow it found itCame back as Step 7 of 7 `intercom.com/help/en/collections/2094824-setting-up-your-workspace` How it got here A link on a page it read Response 200 Came back as Web page 71% Pages that loaded 57% Followed site links 20% Read as markdown How it found each page Named in the question**1** A link on a page it read**4** Typed by the agent**2** A search result**0** What it reached Home page**Step 1** Pricing**Never reached** Docs**Never reached** Its answer Answers aren’t shown publicly See what agents answer about your own site. Run agents on your site and read every answer, with every page they opened. [Get started →](https://app.agentrail.co/login?utm%5Fsource=agentrail.co&utm%5Fmedium=website&utm%5Fcampaign=agent-readiness%2Fintercom.com&utm%5Fcontent=journey-answer) Free to start. No card. Every check 125checks - Passed**30** - To fix**32** - Not in the score**63** 62 checks count toward the score. The other 63 are tracked for later. Discovery18 of 201 to fix1 partly2 passed ARD discoveryRequired0 / 1 Wikipedia / Wikidata entity presenceRecommended2 / 4 Brand name discoverabilityRequired3 / 3 robots.txt AI crawler policyRequired2 / 2 \+ 11 checks not in the score AI Catalog discoveryRecommendedNot counted ARD entry validityRecommendedNot counted ARD trust manifestRecommendedNot counted Category share of voiceRecommendedNot counted Developer resource discoverabilityRecommendedNot counted Listed in MCP registriesRecommendedNot counted NPM/PyPI SDK packageRecommendedNot counted Agent platform configsEmergingNot counted Agent Plugins manifestEmergingNot counted Registry brandingEmergingNot counted ChatGPT app listedRecommendedNot counted Access26 of 302 to fix7 partly16 passed Agent discovery fileRequired0 / 2 A2A / agent-cardRecommended0 / 2 Content without JavaScriptRequired2 / 3 Sitemap freshness (lastmod)Recommended0 / 1 Organization schema completenessRecommended1 / 2 Schema type breadthRecommended1 / 2 Trust anchor pagesRequired1 / 2 Redirect hygieneRecommended0 / 1 API catalog (RFC 9727)Required1 / 2 Sitemap existsRequired2 / 2 Not blocked by bot detectionRequired2 / 2 MCP well-known discoveryRecommended2 / 2 HTTP Link headers (RFC 8288)Required1 / 1 robots.txt agent-user policyRequired2 / 2 llms.txt existsRequired1 / 1 llms.txt formattingRecommended2 / 2 JSON-LD structured dataRequired4 / 4 Pricing info accessibleRequired3 / 3 JSON-LD entity linking (sameAs)Recommended2 / 2 Metadata completenessRequired2 / 2 llms.txt links resolveRecommended2 / 2 Page token budgetRecommended1 / 1 OpenAPI spec publishedRequired7 / 7 Markdown content negotiation (acceptmarkdown.com)Recommended1 / 1 Agent crawler reachabilityRecommended2 / 2 \+ 17 checks not in the score Agent Skills index conformance (v0.2.0)EmergingNot counted Listed on skills.shEmergingNot counted pricing.md existsEmergingNot counted NLWeb Schema FeedsEmergingNot counted Agent mode viewEmergingNot counted Markdown URL fallbackEmergingNot counted Modular llms.txt per product areaEmergingNot counted Public API/docs linked from homepageRequiredNot counted Agent instruction / when-to-useRequiredNot counted Skills.sh skill qualityEmergingNot counted Markdown alternate linkEmergingNot counted Markdown frontmatter metadataEmergingNot counted Code fence validityEmergingNot counted Content behind authRecommendedNot counted Developer portalRecommendedNot counted Markdown agent docsEmergingNot counted Bot-UA markdown servingEmergingNot counted Usability33 of 407 to fix8 partly12 passed auth.md existsRequired0 / 2 auth.md structureRecommended0 / 2 agent\_auth endpoints reachableRecommended0 / 2 Rate limit response headersRecommended0 / 2 Idempotency-Key supportRecommended0 / 3 Sandbox / test environmentRecommended0 / 2 REST batch / bulk endpointRecommended0 / 2 Agent auth discovery metadataRecommended1 / 3 MCP server / manifestRequired5 / 6 REST versioning / deprecation policyRecommended2 / 3 REST async-job patternRecommended1 / 2 MCP server-card.jsonRecommended1 / 2 Agent-friendly 404sRecommended1 / 2 API schema complexity analysisRecommended1 / 2 Function calling compatibilityRecommended1 / 2 Public API with reachable endpointsRequired7 / 7 OAuth 2.0 supportRequired5 / 5 Scoped permissionsRecommended5 / 5 MCP auth mechanismRecommended2 / 2 MCP OAuth metadataRecommended2 / 2 MCP PKCE S256 supportRecommended2 / 2 OAuth Protected Resource metadata (RFC 9728)Required2 / 2 Agent auth WWW-Authenticate hintRecommended1 / 1 JSON error responsesRequired4 / 4 REST typed error modelRecommended3 / 3 Accessible document structureRecommended3 / 3 Accessible names on controlsRecommended2 / 2 \+ 35 checks not in the score MCP tool descriptionsRecommendedNot counted MCP parameter schemasRecommendedNot counted MCP server identityRecommendedNot counted MCP tool listingRecommendedNot counted MCP tool namingRecommendedNot counted Agent onboarding frictionRecommendedNot counted Web Bot Auth directoryEmergingNot counted auth.md walkthrough simulationRecommendedNot counted MCP error handlingRecommendedNot counted MCP modern transportRecommendedNot counted WebMCP supportRequiredNot counted REST pagination patternRecommendedNot counted CLI tool availableRecommendedNot counted Multi-language SDK packagesRecommendedNot counted NLWeb /ask endpointEmergingNot counted NLWeb streaming supportEmergingNot counted REST response schema coverageRecommendedNot counted MCP tool annotationsRecommendedNot counted Product + docs MCP coverageRecommendedNot counted MCP resources exposedRecommendedNot counted GraphQL typed error modelRecommendedNot counted GraphQL versioning / deprecation policyRecommendedNot counted GraphQL pagination patternRecommendedNot counted GraphQL async-job patternRecommendedNot counted GraphQL schema description coverageRecommendedNot counted GraphQL batch mutationsRecommendedNot counted Native interactive controlsRecommendedNot counted Form control labelingRecommendedNot counted Accessibility-tree injection safety (bonus)RecommendedNot counted MCP Apps supportRecommendedNot counted A2UI / generative UI supportEmergingNot counted MCP Apps UI qualityRecommendedNot counted MCP App view reachableRecommendedNot counted MCP App view CSPRecommendedNot counted MCP resource qualityRecommendedNot counted PaymentsNot scored yet6 partly MPP payment protocolRequired0 / 2 x402 payment protocolRequired0 / 2 UCP - Universal Commerce ProtocolRequired0 / 3 ACP - Agentic Commerce ProtocolRequired0 / 3 ACP delegate paymentRecommended0 / 3 AP2 - Agent Payments ProtocolRecommended0 / 3