SEO Audit

Questions for AI search

find_ai_questions

Read-onlyIdempotent

Long-search finder for a pasted Search Console export. Use this when the user pastes Search Console Performance rows or a CSV and asks which questions to answer on their pages, or how to get named in ChatGPT or Google AI answers. Pass the text as csv, or JSON rows as rows, with query and impressions, and page if there is one. Up to 5000 rows. Returns the searches of 7 or more words ranked by impressions, marked when they look like questions. Each has the page Google shows, the question as a heading, and a 2-sentence answer skeleton with a placeholder for one real number or fact that only the owner knows. Also groups by page. It reads only what is pasted: no Google login, no Search Console call, no AI engine. It does not write the answer or invent the number. Not for a user with no export: ask them to paste one.

Input Schema

Name	Required	Description
`csv`	No	Pasted text of a Search Console export: a header row, then one row per search. Needs a query column and an impressions column; a page column, clicks and position are used when present. Comma, semicolon or tab separated. Up to 5000 data rows. Do not pass this together with rows.
`rows`	No	The same data as JSON rows, for example {"query": "how do I ...", "page": "https://example.com/a", "impressions": 120, "clicks": 3, "position": 8.2}. Up to 5000 rows. Do not pass this together with csv.
`limit`	No	Most questions to return, 1 to 50. Default 20.

Output Schema

Name	Required	Description
`asOf`	Yes
`notes`	Yes
`pages`	Yes	The pages that Google shows for these searches, by total impressions.
`steps`	Yes
`notice`	Yes
`source`	Yes
`summary`	Yes
`reminder`	Yes
`questions`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 10, 2026

addedInput schema / anyOf

Added value: +[
+  {
+    "required": [
+      "csv"
+    ]
+  },
+  {
+    "required": [
+      "rows"
+    ]
+  }
+]

addedInput schema / properties / rows / items / description

Added value: +"One search. Search Console column names such as \"Top queries\" are also read."

addedInput schema / properties / rows / items / properties

Added value: +{
+  "clicks": {
+    "type": "number"
+  },
+  "impressions": {
+    "type": "number"
+  },
+  "page": {
+    "description": "The page Google showed.",
+    "type": "string"
+  },
+  "position": {
+    "description": "Average position.",
+    "type": "number"
+  },
+  "query": {
+    "description": "The search as typed.",
+    "type": "string"
+  }
+}

addedInput schema / properties / rows / items / required
```
Added value: +[
+  "query",
+  "impressions"
+]
```

AddedOct 6, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/closed-world, but the description adds real context: no Google login, no Search Console call, no AI engine, it does not write the answer or invent the number, and it caps input at 5000 rows. It also discloses the output shape (ranking, question marking, page grouping, answer skeleton). 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.

Conciseness4/5

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

Purpose and trigger are front-loaded, and most sentences earn their place (exclusions, limits, input mode). However, the long return-value walkthrough partially duplicates the existing output schema, adding mild redundancy.

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 tool with an output schema and full annotation coverage, the description still supplies trigger conditions, input limits, the no-export exclusion, and behavioral boundaries. Nothing an agent needs to select or invoke it 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 coverage is 100%, so csv/rows/limit are already fully documented, including the 'do not pass together' rule. The description restates the csv-vs-rows choice and required fields (query, impressions, page if present) but adds no syntax or format detail beyond the schema, so baseline 3 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 specific verb+resource: 'Long-search finder for a pasted Search Console export,' then states the exact trigger (pasted Performance rows/CSV) and the deliverable (7+ word searches ranked by impressions, question-marked). This is distinguishable from siblings like audit_page, compare_citations, and score_page_citation 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?

Gives explicit when-to-use ('user pastes Search Console Performance rows or a CSV and asks which questions to answer... or how to get named in ChatGPT or Google AI answers') and explicit when-not ('Not for a user with no export: ask them to paste one'). It also names the alternative input mode (csv vs rows) and their mutual exclusivity, leaving nothing to inference.

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.