SEO Audit

Compare cited pages

compare_citations

Read-onlyIdempotent

Citation-pattern check for one query. Use this when the user has the pages an AI answer or Google AI Overview cited for a search and asks what they share, or why their own page is not cited. Pass query, cited_urls (2 to 6 public addresses the user copied from the answer) and exactly one of url, html or text for the user's page. Reads the public pages with robots.txt respected and returns the gaps first: each signal most cited pages share and the user's page lacks (opening answer, query words in a heading, question heading, table, list, date in the last year, links out, schema types, length), with counts such as 4 of 5 and a fix. Every signal is also listed per page. It reads no Google or AI engine, so the user must supply the cited addresses; never guess them. It stores nothing; change over days needs a new call later. A shared signal is a pattern in a small sample, not a proven cause, and no citation is promised. Do not use it for private addresses.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	No	Your page to compare, a public address. Pass exactly one of url, html or text.
`html`	No	Your page as pasted HTML, for a draft that is not published. Nothing is fetched for it.
`text`	No	Your page as pasted text or Markdown.
`query`	Yes	The search or question the AI answer was given for, exactly as typed, such as "best form builder".
`cited_urls`	Yes	The public pages the AI answer cited, 2 to 6 addresses. Copy them by hand from the answer's source list; this tool does not read Google or any AI engine.

Output Schema

TableJSON Schema

Name	Required	Description
`gaps`	Yes	Signals that most cited pages share and your page lacks, with the fix.
`cited`	Yes
`notes`	Yes
`query`	Yes
`track`	Yes	How to see change over days. Nothing is stored.
`yours`	Yes
`notice`	Yes
`readAt`	Yes	Date the pages were read, YYYY-MM-DD.
`reason`	Yes
`signals`	Yes	Every signal, with how many cited pages have it and your page's value.
`readableCited`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 10, 2026

addedInput schema / anyOf

Added value: +[
+  {
+    "required": [
+      "url"
+    ]
+  },
+  {
+    "required": [
+      "html"
+    ]
+  },
+  {
+    "required": [
+      "text"
+    ]
+  }
+]

addedInput schema / properties / cited_urls / items / description

Added value: +"A public page address, such as https://example.com/best-form-builders. A bare domain means https."

changedInput schema / properties / query / description

Previous value: -"The search or question the AI answer was given for, exactly as typed."New value: +"The search or question the AI answer was given for, exactly as typed, such as \"best form builder\"."

AddedOct 7, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the readOnly/openWorld/idempotent annotations, it discloses robots.txt compliance, that nothing is stored, that trend analysis requires re-calling later, that no Google or AI engine is read, and that results are correlational ("a pattern in a small sample, not a proven cause, and no citation is promised"). These are exactly the operational caveats an agent needs and that annotations cannot carry.

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 purpose and usage well, and every section is relevant. However, it spends several sentences enumerating return signals and counts even though an output schema exists, and repeats the "does not read Google" point that the cited_urls schema description already makes.

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?

Covers trigger conditions, the multi-parameter input contract, fetch behavior, storage/statefulness, epistemic limits of the output, and an exclusion. For a 5-parameter comparative analysis tool with a rich output schema, nothing an agent needs to decide or invoke correctly is missing.

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%, and the description largely restates the schema ("Pass query, cited_urls ... and exactly one of url, html or text"), including the exclusivity rule already documented on the url param and the "copy by hand" note already on cited_urls. It adds only soft framing of intent, so the baseline 3 for a fully-documented schema applies.

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?

Opens with a precise verb+resource framing ("Citation-pattern check for one query") and immediately scopes it to comparing the user's page against the pages an AI answer cited. It is clearly distinguishable from siblings like score_page_citation or audit_page, since it is explicitly a multi-page comparative pattern check rather than a single-page score.

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 ("when the user has the pages an AI answer or Google AI Overview cited... and asks what they share, or why their own page is not cited") plus a hard exclusion ("Do not use it for private addresses"). It also states the prerequisite that the user must supply the cited addresses and that the tool cannot fetch them itself, which prevents a whole class of misuse.

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

All SEO 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.