---
title: "Zendesk agent readiness score: 53/100 · Agentrail"
description: "Discovery is the strongest area, with Wikipedia or Wikidata presence and brand name discoverability, while checks for an MCP server or manifest and a published OpenAPI specification were missed."
canonical: "https://www.agentrail.co/agent-readiness/zendesk.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%2Fzendesk.com&utm%5Fcontent=company-report)

Free to start. No card.

Usability

22 to fix

- OAuth 2.0 supportRequiredHow to fix →
- Scoped permissionsRecommendedHow to fix →
- Web Bot Auth directoryEmergingHow to fix →
- OAuth Protected Resource metadata (RFC 9728)RequiredHow to fix →

Fixes unlock with the full report

Where the score comes from

48 of 90 points

How zendesk.com scores on each of the four questions agents ask.

Discovery18/20

Access21/30

Usability9/40

Paymentsnot scored yet

Strongest

### Discovery

ARD discovery is missing.

18/20

Most to gain

### Usability

OAuth 2.0 support, Scoped permissions, and 17 more are missing.

9/40

Most to gain

### Access

Content without JavaScript, Agent discovery file, and 9 more are missing.

21/30

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 zendesk.comand recorded every request it made.

**Z**zendesk.comAnsweredRan Nov 8, 2026

Question

I want to start using Zendesk (zendesk.com). Find its setup and getting-started guide.

21

Steps

1m 54s

Duration

19

Pages opened

7

Failed

6 of 8 addresses the agent typed itself didn’t load. 1 of 10 links it followed didn’t load.

1. 1zendesk.com /Named in the question _→_ **Read**
2. 2/hc/en-usA link on a page it read _→_ **Read**
3. 3/hc/en-us/categoriesTyped by the agent _→_ **Didn’t load · 404**
4. 4/hc/en-us/searchTyped by the agent _→_ **Read**
5. 5/hc/en-us/sectionsTyped by the agent _→_ **Didn’t load · 404**
6. 6/hc/en-usA link on a page it read _→_ **Read**
7. 7zendesk.com /Named in the question _→_ **Read again**
8. 8/hc/en-usA link on a page it read _→_ **Read again**
9. 9/hc/en-us/articlesTyped by the agent _→_ **Didn’t load · 404**
10. 10/hc/en-us/sections/201895973-Getting-StartedTyped by the agent _→_ **Didn’t load · 404**
11. 11/serviceA link on a page it read _→_ **Read**
12. 12/hc/en-us/categories/200021808Typed by the agent _→_ **Didn’t load · 404**
13. 13/registerA link on a page it read _→_ **Read**
14. 14/demoA link on a page it read _→_ **Read**
15. 15/programs/zendesk-communityA link on a page it read _→_ **Read**
16. 16zendesk.com /A link on a page it read _→_ **Didn’t load · 403**
17. 17/documentationA link on a page it read _→_ **Read**
18. 18/hc/en-us/articles/203662046-Getting-started-with-ZendeskTyped by the agent _→_ **Didn’t load · 404**
19. 19/hc/en-us/searchTyped by the agent _→_ **Read**
20. 20/startupsA link on a page it read _→_ **Read**
21. 21zendesk.com /A link on a page it read _→_ **Read**

21/21 steps

StepsHow it found itCame back as

Step 21 of 21

`academy.zendesk.com /`

How it got here

A link on a page it read

Response

200

Came back as

Web page

63%

Pages that loaded

53%

Followed site links

50%

Read as markdown

How it found each page

Named in the question**2**

A link on a page it read**11**

Typed by the agent**8**

A search result**0**

What it reached

Home page**Step 1**

Pricing**Never reached**

Docs**Step 17**

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%2Fzendesk.com&utm%5Fcontent=journey-answer)

Free to start. No card.

Every check

125checks

- Passed**20**
- To fix**37**
- Not in the score**68**

57 checks count toward the score. The other 68 are tracked for later.

Discovery18 of 201 to fix3 passed

ARD discoveryRequired0 / 1

Brand name discoverabilityRequired3 / 3

Wikipedia / Wikidata entity presenceRecommended4 / 4

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

Access21 of 306 to fix5 partly14 passed

Agent discovery fileRequired0 / 2

A2A / agent-cardRecommended0 / 2

MCP well-known discoveryRecommended0 / 2

HTTP Link headers (RFC 8288)Required0 / 1

OpenAPI spec publishedRequired0 / 7

API catalog (RFC 9727)Required0 / 2

Content without JavaScriptRequired2 / 3

llms.txt formattingRecommended1 / 2

Schema type breadthRecommended1 / 2

llms.txt links resolveRecommended1 / 2

Redirect hygieneRecommended0 / 1

Sitemap existsRequired2 / 2

Not blocked by bot detectionRequired2 / 2

Sitemap freshness (lastmod)Recommended1 / 1

robots.txt agent-user policyRequired2 / 2

llms.txt existsRequired1 / 1

JSON-LD structured dataRequired4 / 4

Pricing info accessibleRequired3 / 3

JSON-LD entity linking (sameAs)Recommended2 / 2

Metadata completenessRequired2 / 2

Organization schema completenessRecommended2 / 2

Trust anchor pagesRequired2 / 2

Page token budgetRecommended1 / 1

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

Usability9 of 4018 to fix1 partly3 passed

OAuth 2.0 supportRequired0 / 5

Scoped permissionsRecommended0 / 5

OAuth Protected Resource metadata (RFC 9728)Required0 / 2

auth.md existsRequired0 / 2

auth.md structureRecommended0 / 2

Agent auth discovery metadataRecommended0 / 3

Agent auth WWW-Authenticate hintRecommended0 / 1

agent\_auth endpoints reachableRecommended0 / 2

MCP server / manifestRequired0 / 6

WebMCP supportRequired0 / 5

Rate limit response headersRecommended0 / 2

Idempotency-Key supportRecommended0 / 3

REST typed error modelRecommended0 / 3

REST async-job patternRecommended0 / 2

Sandbox / test environmentRecommended0 / 2

REST batch / bulk endpointRecommended0 / 2

API schema complexity analysisRecommended0 / 2

Function calling compatibilityRecommended0 / 2

Agent-friendly 404sRecommended1 / 2

JSON error responsesRequired4 / 4

Accessible document structureRecommended3 / 3

Accessible names on controlsRecommended2 / 2

\+ 40 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

Public API with reachable endpointsRequiredNot counted

MCP auth mechanismRecommendedNot counted

MCP OAuth metadataRecommendedNot counted

MCP PKCE S256 supportRecommendedNot counted

Agent onboarding frictionRecommendedNot counted

Web Bot Auth directoryEmergingNot counted

auth.md walkthrough simulationRecommendedNot counted

MCP error handlingRecommendedNot counted

MCP modern transportRecommendedNot counted

REST versioning / deprecation policyRecommendedNot 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

MCP server-card.jsonRecommendedNot 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
