SEO GSC Wizard MCP

Score an SEO experiment

get_experiment_results

Read-only

Use this when the user asks whether an SEO experiment (split test) worked or which variant won. Scores one SEO experiment: assigns the property's landing pages to the experiment's control and variant URL groups, then compares each variant against the control (group 0) on click growth period-over-period. Returns per-group clicks/impressions/CTR (0-100, with a confidence interval) and an impression-weighted average position, plus for each variant the uplift in growth (percentage points) with its CI, a significance test of that growth difference (significant exactly when the CI excludes 0), the winner, and a low-power warning. ctrPValue is a separate test of the CTR difference, for reference only. The comparison window is the prior same-length period. groups keep the experiment's order (control first) and comparisons follow its variants. Not for finding an experiment or its id: use list_experiments. Reads the ClickHouse warehouse when available, else the live Search Console API.

Input Schema

Name	Required	Description
`endDate`	No	Optional. Window end as YYYY-MM-DD (e.g. 2026-05-31). You do NOT need to know today's date or the latest available date: omit this and the server uses the latest settled Search Console date (data lags ~2-3 days behind today). Never pass null or the string "null".
`siteUrl`	Yes
`startDate`	No	Optional. Window start as YYYY-MM-DD (e.g. 2026-05-03). You do NOT need to know today's date. Omit BOTH startDate and endDate to analyze the last 28 settled days automatically (Search Console data lags ~2-3 days). Never pass null or the string "null".
`experimentId`	Yes	The experiment id from list_experiments.
`confidenceLevel`	No	Confidence level for the significance test and CIs (default 0.95).

Output Schema

Name	Required	Description	Default
`note`	No
`range`	No
`groups`	No
`siteUrl`	No
`nextStep`	No
`truncated`	No
`comparison`	No
`dataSource`	No
`experiment`	No
`comparisons`	No
`emptyBecause`	No
`methodLimits`	No
`truncationNote`	No
`windowNormalization`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 18, 2026

changedOutput schema / additionalProperties
```
Previous value: -falseNew value: +true
```

addedOutput schema / properties / emptyBecause

Added value: +{
+  "$ref": "#/properties/siteUrl"
+}

addedOutput schema / properties / methodLimits

Added value: +{
+  "$ref": "#/properties/siteUrl"
+}

addedOutput schema / properties / nextStep

Added value: +{
+  "$ref": "#/properties/siteUrl"
+}

changedOutput schema / properties / range / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "days": {
-        "type": [
-          "number",
-          "null"
-        ]
-      },
-      "endDate": {
-        "$ref": "#/properties/siteUrl"
-      },
-      "startDate": {
-        "$ref": "#/properties/siteUrl"
-      }
-    },
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": true,
+    "properties": {
+      "days": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "endDate": {
+        "$ref": "#/properties/siteUrl"
+      },
+      "startDate": {
+        "$ref": "#/properties/siteUrl"
+      }
+    },
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / windowNormalization / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "comparisonDays": {
-        "$ref": "#/properties/range/anyOf/0/properties/days"
-      },
-      "currentDays": {
-        "$ref": "#/properties/range/anyOf/0/properties/days"
-      },
-      "note": {
-        "$ref": "#/properties/siteUrl"
-      },
-      "scale": {
-        "$ref": "#/properties/range/anyOf/0/properties/days"
-      }
-    },
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": true,
+    "properties": {
+      "comparisonDays": {
+        "$ref": "#/properties/range/anyOf/0/properties/days"
+      },
+      "currentDays": {
+        "$ref": "#/properties/range/anyOf/0/properties/days"
+      },
+      "note": {
+        "$ref": "#/properties/siteUrl"
+      },
+      "scale": {
+        "$ref": "#/properties/range/anyOf/0/properties/days"
+      }
+    },
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

Changed3 schema fields changedOct 10, 2026

addedOutput schema / properties / truncated

Added value: +{
+  "type": [
+    "boolean",
+    "null"
+  ]
+}

addedOutput schema / properties / truncationNote

Added value: +{
+  "$ref": "#/properties/siteUrl"
+}

addedOutput schema / properties / windowNormalization

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "comparisonDays": {
+          "$ref": "#/properties/range/anyOf/0/properties/days"
+        },
+        "currentDays": {
+          "$ref": "#/properties/range/anyOf/0/properties/days"
+        },
+        "note": {
+          "$ref": "#/properties/siteUrl"
+        },
+        "scale": {
+          "$ref": "#/properties/range/anyOf/0/properties/days"
+        }
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

First observedOct 7, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, but the description adds substantial behavioral context beyond them: the comparison window is the prior same-length period, significance is defined as the CI excluding 0, groups preserve experiment order, and the data source falls back from the ClickHouse warehouse to the live Search Console API. None of that is derivable from the structured fields.

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?

The trigger condition and the sibling exclusion bracket the body, which is the right front-loading. The middle enumeration of returned statistics is dense and slightly over-long given an output schema exists, but each clause carries information rather than filler.

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 read-only analytical tool with an output schema and full annotation coverage, the description supplies everything else an agent needs: the exact comparison logic, the window definition, group ordering, significance semantics, the data-source fallback, and the hand-off to list_experiments for experiment discovery.

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 80% and the schema itself documents startDate/endDate defaults, the 'never pass null' rule, the date format and the confidenceLevel range and default. The description adds no parameter-level detail (e.g. it never mentions confidenceLevel or the date window semantics it relies on), so this sits at the baseline where the schema does the heavy lifting.

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 and resource ('Scores one SEO experiment') plus the exact scope of what is compared (control group 0 vs each variant, click growth period-over-period). It explicitly distinguishes itself from the sibling list_experiments, so an agent can route without opening either 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?

Opens with the trigger condition ('Use this when the user asks whether an SEO experiment (split test) worked or which variant won') and closes with an explicit exclusion plus the alternative ('Not for finding an experiment or its id: use list_experiments'). Both when-to-use and when-not-to-use are covered.

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

All SEO GSC Wizard MCP 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.

Resources

Need Help?