Specularis AI Visibility Audit

Run AI Visibility Audit

run_ai_visibility_audit

Run a free AI visibility (GEO/AEO) audit on a website — checks whether ChatGPT, Claude, Perplexity, and Gemini can find and cite it. Returns an instant snapshot of crawler access, structured data, and llms.txt. If an email is provided, a full scored report (0–100 across 5 pillars, with copy-paste fixes) is emailed as a PDF. Use this whenever a user asks to audit/check a site's AI visibility, GEO, AEO, or whether AI can find them.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "website_url": "<website_url>"
    },
    "name": "run_ai_visibility_audit"
  }
}

Input Schema

Name	Required	Description
`name`	No	Optional name for the report greeting.
`role`	No	Optional. Tailors the audit lens — local-service providers are scored on local entity signals, reviews, and directories.
`email`	No	Optional. If provided, the full scored PDF report is emailed here (and the user becomes a Specularis lead). Omit for just the instant snapshot.
`website_url`	Yes	The website to audit, e.g. https://example.com

Output Schema

Name	Required	Description
`website`	Yes	The normalized website that was audited.
`llms_txt`	Yes	Whether an llms.txt file is present.
`booking_url`	Yes	Link to book a Specularis strategy call.
`report_email`	No	The email the full report was sent to, if requested.
`structured_data`	Yes	Summary of JSON-LD structured data found on the homepage.
`ai_crawler_access`	Yes	Whether major AI crawlers (GPTBot, ClaudeBot, PerplexityBot) can access the site.
`full_report_status`	Yes	Status of the full scored PDF report.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedAug 3, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "ai_crawler_access": {
+      "description": "Whether major AI crawlers (GPTBot, ClaudeBot, PerplexityBot) can access the site.",
+      "type": "string"
+    },
+    "booking_url": {
+      "description": "Link to book a Specularis strategy call.",
+      "type": "string"
+    },
+    "full_report_status": {
+      "description": "Status of the full scored PDF report.",
+      "enum": [
+        "sent",
+        "failed",
+        "not_requested"
+      ],
+      "type": "string"
+    },
+    "llms_txt": {
+      "description": "Whether an llms.txt file is present.",
+      "type": "string"
+    },
+    "report_email": {
+      "description": "The email the full report was sent to, if requested.",
+      "type": "string"
+    },
+    "structured_data": {
+      "description": "Summary of JSON-LD structured data found on the homepage.",
+      "type": "string"
+    },
+    "website": {
+      "description": "The normalized website that was audited.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "website",
+    "ai_crawler_access",
+    "structured_data",
+    "llms_txt",
+    "full_report_status",
+    "booking_url"
+  ],
+  "type": "object"
+}

First observedAug 2, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations show readOnlyHint=false and openWorldHint=true, and the description honestly discloses the nontrivial side effect that providing an email 'becomes a Specularis lead' and triggers a PDF email. It also clarifies that omitting email yields only the instant snapshot, so the agent understands both behavioral paths. No contradiction with annotations.

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?

Three sentences, each earning its place: definition, conditional output behavior, and usage trigger. The most important scoping information is front-loaded in the first sentence. No filler or repetition.

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

Completeness4/5

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

For a tool with 4 params, an output schema, and meaningful optional behavior, the description covers the audit scope, snapshot contents, scored report, email side effect, and when to invoke it. It doesn't mention sibling routing or timing expectations, but those are covered by annotations and schema context and are not essential to a correct call.

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 already documents all four parameters with 100% coverage, so baseline is 3. The description adds meaning beyond the schema by explaining the behavioral consequence of the email parameter (lead creation + emailed PDF) and confirming that website_url is the audit target. It does not add new detail for name/role, but the schema covers those adequately.

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?

The description opens with a specific verb and object — 'Run a free AI visibility (GEO/AEO) audit on a website' — and defines the tool's scope by naming the AI engines it checks (ChatGPT, Claude, Perplexity, Gemini). It is unambiguous about what the tool does, but it does not explicitly differentiate from siblings like find_ai_citations or book_strategy_call. That prevents a 5.

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?

It provides an explicit trigger condition: 'Use this whenever a user asks to audit/check a site's AI visibility, GEO, AEO, or whether AI can find them.' It also clarifies the conditional path for email vs. omit-email. However, it does not state when to prefer a sibling tool or what counts as a non-audit request, so it stops short of full when/when-not guidance.

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

All Specularis AI Visibility 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.