Site Check

Check AI readiness of a store or page

ai_readiness_check

Read-onlyIdempotent

Checks if AI agents can read and cite a site or page. Use it when the user asks whether AI agents and assistants can read an online store or cite a page, for example "can AI shopping agents read my store?", "will AI assistants cite this page, and what should I fix?", "does shop.example.com have an llms.txt?" or "does my store publish a UCP file?". Pass the page url or domain. Returns whether the domain has /llms.txt, /agents.md, the Universal Commerce Protocol file at /.well-known/ucp (published by Shopify stores; version and listed services are shown) and a /sitemap.xml, plus which of 14 AI crawlers robots.txt blocks for the whole site, and lists present and missing files. When a page address is checked, it evaluates five AI citation signals: a clear summary near the top, author name and credentials, Q&A or FAQ format, clear heading structure, and structured data, each with pass, warn or fail, evidence and a concrete fix. It requests at most five domain files and one page, skips any that robots.txt disallows for Agent Tools, and shows what is published, not whether an agent can complete a purchase. Do not use it for private or local addresses, to read page content, or to scan for vulnerabilities.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	No	Address of one public web page to check for AI citation signals (clear summary, author credentials, Q&A format, heading structure, structured data), for example https://example.com/blog/guide. A bare domain means https. When provided, the page is checked for citation signals alongside domain files.
`domain`	No	Domain of a public store or website, for example shop.example.com. Used when checking domain files only (llms.txt, agents.md, UCP, sitemap, AI crawler rules).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ucp`	No
`page`	No
`notes`	No
`domain`	Yes
`notice`	Yes
`origin`	No
`robots`	No
`source`	Yes
`failure`	No
`llmsTxt`	No
`missing`	No
`present`	No
`sitemap`	No
`agentsMd`	No
`platform`	No
`reachable`	Yes
`citationChecks`	No
`citationSummary`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 3, 2026

changedInput schema / properties / domain / description

Previous value: -"Domain of a public store or website, for example shop.example.com. Only the host is used. A full address is accepted and reduced to its host."New value: +"Domain of a public store or website, for example shop.example.com. Used when checking domain files only (llms.txt, agents.md, UCP, sitemap, AI crawler rules)."

addedInput schema / properties / url

Added value: +{
+  "description": "Address of one public web page to check for AI citation signals (clear summary, author credentials, Q&A format, heading structure, structured data), for example https://example.com/blog/guide. A bare domain means https. When provided, the page is checked for citation signals alongside domain files.",
+  "maxLength": 2048,
+  "minLength": 3,
+  "type": "string"
+}

removedInput schema / required
```
Removed value: -[
-  "domain"
-]
```

addedOutput schema / properties / citationChecks

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "evidence": {
+        "type": "string"
+      },
+      "fix": {
+        "type": "string"
+      },
+      "id": {
+        "enum": [
+          "summary_clarity",
+          "author_credentials",
+          "qa_format",
+          "heading_structure",
+          "structured_data"
+        ],
+        "type": "string"
+      },
+      "status": {
+        "enum": [
+          "pass",
+          "warn",
+          "fail"
+        ],
+        "type": "string"
+      },
+      "title": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "status",
+      "title",
+      "evidence",
+      "fix"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / citationSummary

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "fail": {
+      "type": "integer"
+    },
+    "pass": {
+      "type": "integer"
+    },
+    "warn": {
+      "type": "integer"
+    }
+  },
+  "required": [
+    "pass",
+    "warn",
+    "fail"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / page

Added value: +{
+  "properties": {
+    "blockedByRobots": {
+      "type": "boolean"
+    },
+    "failure": {
+      "type": "string"
+    },
+    "finalUrl": {
+      "type": "string"
+    },
+    "note": {
+      "type": "string"
+    },
+    "status": {
+      "type": "integer"
+    },
+    "url": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

First observedOct 3, 2026

TDQS

A4.3/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this read-only, idempotent and non-destructive, but the description goes well beyond them: it discloses the request budget ('at most five domain files and one page'), the robots.txt compliance behavior for Agent Tools, the exact composition of the result set, and the limitation that publication is not proof of agent capability.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and trigger examples are front-loaded, which is good, but the middle section is a single dense run-on enumerating every returned artifact and all five citation signals. With an output schema present, that return-value detail is largely redundant and inflates the definition without adding selection value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only inspection tool with two optional parameters, an output schema and four annotations, the description covers everything an agent needs: what it inspects, what it returns, what it will not do, and the network footprint. No material decision-relevant gap remains.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the two parameters (url, domain) are already fully documented, including the https default for bare domains and what each one triggers. The description only restates 'Pass the page url or domain' and adds no format, precedence or interaction rules beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Checks if AI agents can read and cite a site or page') and enumerates the concrete artifacts it inspects (llms.txt, agents.md, UCP, sitemap, crawler rules, five citation signals). It does not, however, differentiate itself from overlapping siblings such as check_ai_crawler_access, landing_page_check or check_page_tags, which an agent could plausibly confuse with this one.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit trigger conditions with four verbatim user phrasings ('can AI shopping agents read my store?', 'does shop.example.com have an llms.txt?', etc.) plus explicit exclusions: private/local addresses, reading page content, vulnerability scanning. It also bounds the claim ('shows what is published, not whether an agent can complete a purchase'), removing a likely false expectation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Site Check tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?