SurfacedBy AI Visibility & GEO Audit

Audit website pages the way AI reads them

surfacedby_inspect_page_evidence

Read-onlyIdempotent

Read up to five public pages the way an AI crawler receives them, without running JavaScript. Returns sourced sections, table cells, internal and outside links and declared structured data, plus each page's type, source type and readiness findings with the documentation behind them, repeated declared facts to review, and the remaining request budget. Partial or unreadable pages are reported as such. Runs no AI queries and measures no visibility.

Input Schema

Name	Required	Description	Default
`urls`	Yes

Output Schema

Name	Required	Default
`pages`	Yes
`budget`	No
`status`	Yes
`next_steps`	No
`limitations`	No
`evidence_kind`	No	public_page_inspection
`evidence_provider`	No	SurfacedBy
`declaration_review`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedOct 12, 2026

addedOutput schema / $defs / Budget

Added value: +{
+  "additionalProperties": false,
+  "description": "Remaining shared outbound allowance, so a model can plan its next calls.\nCached evidence costs nothing; every fresh request counts, including\nrobots.txt reads and redirects.",
+  "properties": {
+    "daily_remaining": {
+      "title": "Daily Remaining",
+      "type": "integer"
+    },
+    "monthly_remaining": {
+      "title": "Monthly Remaining",
+      "type": "integer"
+    },
+    "per_site_daily_limit": {
+      "title": "Per Site Daily Limit",
+      "type": "integer"
+    },
+    "sites_remaining_today": {
+      "additionalProperties": {
+        "type": "integer"
+      },
+      "title": "Sites Remaining Today",
+      "type": "object"
+    }
+  },
+  "required": [
+    "daily_remaining",
+    "monthly_remaining",
+    "per_site_daily_limit"
+  ],
+  "title": "Budget",
+  "type": "object"
+}

addedOutput schema / $defs / NextStep

Added value: +{
+  "additionalProperties": false,
+  "description": "A deterministic pointer to the audit step this result supports next.",
+  "properties": {
+    "action": {
+      "title": "Action",
+      "type": "string"
+    },
+    "step": {
+      "title": "Step",
+      "type": "string"
+    },
+    "tool": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Tool"
+    }
+  },
+  "required": [
+    "step",
+    "action"
+  ],
+  "title": "NextStep",
+  "type": "object"
+}

changedOutput schema / $defs / PageEvidence / properties / extraction_version / default
```
Previous value: -"5"New value: +"6"
```

addedOutput schema / $defs / PageEvidence / properties / page_type

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Page Type"
+}

addedOutput schema / $defs / PageEvidence / properties / readiness

Added value: +{
+  "anyOf": [
+    {
+      "$ref": "#/$defs/PageReadiness"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

addedOutput schema / $defs / PageEvidence / properties / source_type

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Source Type"
+}

addedOutput schema / $defs / PageReadiness

Added value: +{
+  "additionalProperties": false,
+  "description": "How a non-JavaScript reader receives the page, from the readiness rules.",
+  "properties": {
+    "canonical_points_elsewhere": {
+      "anyOf": [
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Canonical Points Elsewhere"
+    },
+    "canonical_url": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Canonical Url"
+    },
+    "findings": {
+      "items": {
+        "$ref": "#/$defs/ReadinessFinding"
+      },
+      "title": "Findings",
+      "type": "array"
+    },
+    "indexing": {
+      "enum": [
+        "indexable",
+        "noindex",
+        "unknown"
+      ],
+      "title": "Indexing",
+      "type": "string"
+    },
+    "limitations": {
+      "items": {
+        "type": "string"
+      },
+      "title": "Limitations",
+      "type": "array"
+    },
+    "minor_findings": {
+      "items": {
+        "type": "string"
+      },
+      "title": "Minor Findings",
+      "type": "array"
+    },
+    "rendering": {
+      "enum": [
+        "readable",
+        "shell",
+        "unknown"
+      ],
+      "title": "Rendering",
+      "type": "string"
+    },
+    "schema_types": {
+      "items": {
+        "type": "string"
+      },
+      "title": "Schema Types",
+      "type": "array"
+    }
+  },
+  "required": [
+    "rendering",
+    "indexing"
+  ],
+  "title": "PageReadiness",
+  "type": "object"
+}

addedOutput schema / $defs / ReadinessFinding

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "action": {
+      "title": "Action",
+      "type": "string"
+    },
+    "category": {
+      "title": "Category",
+      "type": "string"
+    },
+    "detail": {
+      "title": "Detail",
+      "type": "string"
+    },
+    "documentation": {
+      "title": "Documentation",
+      "type": "string"
+    },
+    "impact": {
+      "title": "Impact",
+      "type": "string"
+    },
+    "rule": {
+      "title": "Rule",
+      "type": "string"
+    },
+    "severity": {
+      "enum": [
+        "high",
+        "medium"
+      ],
+      "title": "Severity",
+      "type": "string"
+    },
+    "title": {
+      "title": "Title",
+      "type": "string"
+    }
+  },
+  "required": [
+    "rule",
+    "category",
+    "severity",
+    "title",
+    "impact",
+    "action",
+    "detail",
+    "documentation"
+  ],
+  "title": "ReadinessFinding",
+  "type": "object"
+}

addedOutput schema / properties / budget

Added value: +{
+  "anyOf": [
+    {
+      "$ref": "#/$defs/Budget"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

addedOutput schema / properties / next_steps

Added value: +{
+  "items": {
+    "$ref": "#/$defs/NextStep"
+  },
+  "title": "Next Steps",
+  "type": "array"
+}

First observedOct 10, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds meaningful behavior beyond that: no JavaScript execution, a five-page cap, partial/unreadable pages are reported rather than silently dropped, and the response includes the remaining request budget (an implicit quota cue).

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

Conciseness4/5

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

Front-loads the core action, then sequences returns, failure handling and scope exclusions in two short follow-on sentences. The return enumeration is dense but every element earns its place; nothing is padding.

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?

An output schema exists, so return values need not be restated, yet the description still frames them usefully. Combined with the JS-off caveat, page cap, partial-page reporting and budget disclosure, an agent has everything needed to invoke this correctly.

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?

There is a single parameter with 0% schema description coverage, so the description must carry the semantics. It contributes the constraint that pages must be 'public' and repeats the five-item cap already encoded in maxItems, but adds no format or syntax guidance for the urls array.

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

Purpose5/5

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

States a specific verb (read) and resource (public pages as an AI crawler receives them) with a hard scope (up to five, no JavaScript), and enumerates exactly what the result contains. This is clearly distinguishable from siblings like surfacedby_analyze_answer_evidence and surfacedby_check_ai_crawler_access.

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

Usage Guidelines4/5

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

Gives clear usage context (auditing how AI crawlers see pages) and a negative exclusion ('Runs no AI queries and measures no visibility'), which tells the agent what this tool is not for. It never names the sibling that should be used instead for those tasks, so it stops short of full when/when-not routing.

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

All SurfacedBy AI Visibility & GEO Audit 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.