google-search-console-mcp-server

gsc detect cannibalization

gsc_detect_cannibalization

Read-onlyIdempotent

Detect keyword cannibalization by identifying Search Console queries where multiple pages compete for clicks and impressions, helping you find pages to consolidate or reoptimize.

Instructions

Detect queries where multiple pages compete for clicks/impressions in Search Analytics query-page rows.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`topN`	No	Maximum number of highest-ranked results to return.
`limit`	No	Maximum number of returned items or rows. The declared bounds and default apply; use pagination for additional results.
`siteUrl`	No	Search Console property URL, e.g. https://example.com/ or sc-domain:example.com. Uses GSC_SITE_URL when omitted.
`minPages`	No	Minimum distinct pages ranking for a query before it is considered a cannibalization candidate.
`dateRange`	No	Explicit reporting start and end dates in YYYY-MM-DD format.
`datePreset`	No	Named reporting period. Use the custom date range when you need exact start and end dates.	last28days
`searchType`	No	Search surface to report, such as web, image, video, news or Discover. Availability depends on the property.	web
`minImpressions`	No	Minimum reported impressions required for a row to enter the analysis.
`maxTopPageClickShare`	No	Only flag queries where the top page owns less than or equal to this click share.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes	Original tool result: parsed JSON when the text is JSON, otherwise the text or multiple MCP content blocks. Provider fields depend on the selected query.

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedv2.0.0Oct 4, 2026

addedInput schema / properties / datePreset / description

Added value: +"Named reporting period. Use the custom date range when you need exact start and end dates."

addedInput schema / properties / dateRange / description

Added value: +"Explicit reporting start and end dates in YYYY-MM-DD format."

addedInput schema / properties / limit / description

Added value: +"Maximum number of returned items or rows. The declared bounds and default apply; use pagination for additional results."

addedInput schema / properties / minImpressions / description

Added value: +"Minimum reported impressions required for a row to enter the analysis."

addedInput schema / properties / minPages / description

Added value: +"Minimum distinct pages ranking for a query before it is considered a cannibalization candidate."

addedInput schema / properties / searchType / description

Added value: +"Search surface to report, such as web, image, video, news or Discover. Availability depends on the property."

addedInput schema / properties / topN / description

Added value: +"Maximum number of highest-ranked results to return."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "result": {
+      "anyOf": [
+        {
+          "additionalProperties": true,
+          "properties": {},
+          "type": "object"
+        },
+        {
+          "items": {},
+          "type": "array"
+        },
+        {
+          "type": "string"
+        },
+        {
+          "type": "number"
+        },
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Original tool result: parsed JSON when the text is JSON, otherwise the text or multiple MCP content blocks. Provider fields depend on the selected query."
+    }
+  },
+  "required": [
+    "result"
+  ],
+  "type": "object"
+}

First observedv1.0.0Aug 29, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds useful context by specifying the data source and unit of analysis ('Search Analytics query-page rows'), but it does not reveal additional behavioral traits such as thresholds or analysis methodology beyond what the schema already documents.

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?

A single sentence that is immediately informative and contains no filler. The core action and the subject being analyzed are front-loaded, making the description easy to scan and act on.

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?

Given the rich input schema with 100% parameter coverage, the presence of an output schema, and strong annotations, the one-line description is nearly sufficient. It could briefly mention the detection criteria, such as minPages and maxTopPageClickShare, but the schema already covers those details, so nothing critical is missing for an agent to invoke it 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?

Schema description coverage is 100%, so every parameter is already documented with descriptions, defaults, and bounds. The description adds no extra parameter-level meaning, matching the baseline of 3 for high schema coverage with no additional parameter guidance.

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?

The description uses a specific verb, 'Detect', and names a precise resource: queries where multiple pages compete for clicks/impressions in Search Analytics query-page rows. It clearly defines the cannibalization concept the tool addresses, which distinguishes it from sibling tools like gsc_query_search_analytics and gsc_cluster_queries.

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

Usage Guidelines3/5

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

The description implies when to use the tool: whenever a user wants to identify cannibalization among pages for the same query. However, it does not explicitly state when not to use it or mention alternative sibling tools, so the selection guidance is left mostly to inference.

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