AI-SEO / AEO / GEO Audit

Audit JSON-LD schema

audit_schema

Read-onlyIdempotent

Validate JSON-LD structured data against Schema.org rules and AI-citation best practices. Accepts either a URL (fetched) or a raw JSON string (parsed directly).

Read-only when given url (one HTTP GET). Zero network when given schema_json. No writes.

Deterministic, rule-based; no LLM. Validates required/recommended properties, @context correctness, sameAs links, and AI-search-friendly patterns.

When to use: focused JSON-LD audits, or to validate a schema block you're about to ship. For a full page audit that includes schema + everything else, use audit_page instead.

Either url or schema_json must be provided (not both). If both are provided, schema_json wins and no fetch happens.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	No	Public URL to fetch and audit. Either this OR `schema_json` is required. Read-only HTTP GET.
`schema_json`	No	Raw JSON-LD as a string (the contents of a `<script type="application/ld+json">` block). Use this to validate a schema block offline without fetching a URL. Either this OR `url` is required.
`respect_robots`	No	If true (default), respect robots.txt before fetching `url`. Ignored when `schema_json` is used.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`source`	Yes
`findings`	Yes
`found_types`	Yes
`missing_priority_types`	Yes
`ai_citation_readiness_score`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed22 schema fields changedOct 13, 2026

removedOutput schema / properties / ai_citation_readiness_score / description
```
Removed value: -"0-100 score for the JSON-LD's AI-citation readiness."
```

removedOutput schema / properties / fetched_at

Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}

removedOutput schema / properties / findings / items / properties / category / description
```
Removed value: -"Finding category - which AI-SEO dimension it relates to."
```

addedOutput schema / properties / findings / items / properties / estimated_impact / anyOf

Added value: +[
+  {
+    "not": {}
+  },
+  {
+    "const": "high",
+    "type": "string"
+  },
+  {
+    "const": "medium",
+    "type": "string"
+  },
+  {
+    "const": "low",
+    "type": "string"
+  }
+]

removedOutput schema / properties / findings / items / properties / estimated_impact / description
```
Removed value: -"Estimated impact on AI citation probability when resolved."
```
removedOutput schema / properties / findings / items / properties / estimated_impact / enum
```
Removed value: -[
-  "high",
-  "medium",
-  "low"
-]
```
removedOutput schema / properties / findings / items / properties / estimated_impact / type
```
Removed value: -"string"
```
addedOutput schema / properties / findings / items / properties / failure_signal / anyOf
```
Added value: +[
+  {
+    "not": {}
+  },
+  {
+    "type": "string"
+  }
+]
```

removedOutput schema / properties / findings / items / properties / failure_signal / description

Removed value: -"Falsifiability: the observable signal that would prove the fix did NOT work."

removedOutput schema / properties / findings / items / properties / failure_signal / type
```
Removed value: -"string"
```
removedOutput schema / properties / findings / items / properties / fix / description
```
Removed value: -"Concrete, copy-pasteable fix."
```
addedOutput schema / properties / findings / items / properties / leading_indicator / anyOf
```
Added value: +[
+  {
+    "not": {}
+  },
+  {
+    "type": "string"
+  }
+]
```

removedOutput schema / properties / findings / items / properties / leading_indicator / description

Removed value: -"Falsifiability: the leading indicator to monitor to confirm the fix is landing."

removedOutput schema / properties / findings / items / properties / leading_indicator / type
```
Removed value: -"string"
```
removedOutput schema / properties / findings / items / properties / message / description
```
Removed value: -"Human-readable description of the issue."
```

removedOutput schema / properties / findings / items / properties / severity / description

Removed value: -"Triage priority: critical blocks AI citation, warning hurts probability, info is nice-to-have."

removedOutput schema / properties / findings / items / properties / where / description

Removed value: -"Location of the issue (CSS selector, JSON-LD path, robots.txt line, or 'page-level')."

removedOutput schema / properties / found_types / description

Removed value: -"Schema.org @type values discovered across all JSON-LD blocks."

addedOutput schema / properties / missing_priority_types

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

removedOutput schema / properties / source / description
```
Removed value: -"Where the JSON-LD came from."
```

removedOutput schema / properties / url

Removed value: -{
-  "description": "Source URL (null when source=inline).",
-  "type": [
-    "string",
-    "null"
-  ]
-}

changedOutput schema / required

Previous value: -[
-  "source",
-  "url",
-  "fetched_at",
-  "found_types",
-  "ai_citation_readiness_score",
-  "findings"
-]New value: +[
+  "source",
+  "found_types",
+  "missing_priority_types",
+  "findings",
+  "ai_citation_readiness_score"
+]

First observedOct 2, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, but the description goes well beyond them: it discloses the exact network behavior per mode (one HTTP GET for url, zero network for schema_json), that it is deterministic/rule-based with no LLM, and what it validates. This is genuinely additive context.

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

Conciseness5/5

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

Front-loads the core purpose, then behavior, then usage routing in short scannable sentences. Every sentence carries new information with no restatement of the name or schema.

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?

Inputs, mode-specific behavior, precedence rules, and sibling routing are all covered; an output schema exists so return values need not be described. Nothing an agent needs to invoke this correctly is missing.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds meaning the schema does not: mutual exclusivity of url/schema_json and, critically, the precedence rule that schema_json wins and no fetch occurs when both are supplied.

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 (validate) and resource (JSON-LD structured data) with scope (Schema.org rules, AI-citation best practices). It explicitly distinguishes itself from the sibling audit_page, so an agent can choose correctly without opening any schema.

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?

Provides an explicit 'When to use' line, names the alternative (audit_page) and the condition that selects it (full page audit), and explains the url-vs-schema_json input selection. Nothing is left to inference.

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

All AI-SEO / AEO / GEO Audit tools Inspect

Try in Browser

Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?