Google Ads by Get MCP Ads

Overview Schema Source Related Servers Discussions Admin

google ads generate keyword ideas

google_ads_generate_keyword_ideas

Read-onlyIdempotent

Generate Keyword Planner ideas from seed keywords, a URL, or a whole site, returning volume, trends, competition, and bids for ad planning.

Instructions

Discover Keyword Planner ideas from up to 20 seed keywords, a URL, keywords plus URL, or a whole site. Returns historical volume, monthly trends, computed 3-month/YoY changes, competition, bids, close variants, optional concepts, and pagination. Read-only; no plan is saved.

Input Schema

Name	Required	Description	Default
`url`	No	Specific page URL to crawl; combine with seedKeywords if desired
`site`	No	Whole-domain seed; exclusive with seedKeywords/url
`network`	No	Google Ads search network selector used for planning.	GOOGLE_SEARCH
`pageSize`	No	Google supports up to 10,000; keep pages small for interactive MCP use and use larger pages only for controlled exports
`pageToken`	No	nextPageToken from a prior identical request
`customerId`	Yes	Google Ads serving customer ID; use the client account, not its MCC manager
`languageId`	No	Google Ads language constant ID for the keyword request.
`endYearMonth`	No	Last year and month of the historical metrics period.
`geoTargetIds`	No	Google Ads geo-target constant IDs for the intended locations.
`seedKeywords`	No	Seed keyword phrases from which Google generates keyword ideas.
`historyMonths`	No	13 months is enough to compute latest-month YoY while limiting response size
`startYearMonth`	No	First year and month of the historical metrics period.
`includeAverageCpc`	No	Request average cost-per-click metrics when available.
`includeAdultKeywords`	No	Allow adult keyword ideas where supported by the provider and the selected market.
`includeDeviceBreakdown`	No	Include device-specific planning metrics when supported.
`includeKeywordConcepts`	No	Include Google's keyword concept grouping metadata.

Output 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 changedv2.1.1Oct 30, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```
removedInput schema / properties / endYearMonth / $ref
```
Removed value: -"#/properties/startYearMonth"
```
addedInput schema / properties / endYearMonth / pattern
```
Added value: +"^\\d{4}-(0[1-9]|1[0-2])$"
```
addedInput schema / properties / endYearMonth / type
```
Added value: +"string"
```

removedInput schema / properties / languageId / $ref

Removed value: -"#/properties/geoTargetIds/items"

addedInput schema / properties / languageId / pattern
```
Added value: +"^\\d+$"
```
addedInput schema / properties / languageId / type
```
Added value: +"string"
```

changedOutput schema / properties / result / anyOf

Previous value: -[
-  {
-    "additionalProperties": true,
-    "properties": {},
-    "type": "object"
-  },
-  {
-    "items": {},
-    "type": "array"
-  },
-  {
-    "type": "string"
-  },
-  {
-    "type": "number"
-  },
-  {
-    "type": "boolean"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": {},
+    "properties": {},
+    "type": "object"
+  },
+  {
+    "items": {},
+    "type": "array"
+  },
+  {
+    "type": "string"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "boolean"
+  },
+  {
+    "type": "null"
+  }
+]

First observedv2.0.1Sep 23, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so 'Read-only; no plan is saved' mainly confirms the safety profile while adding the useful fact that no plan persists. The enumeration of returned fields (volume, trends, YoY, competition, bids, variants, concepts, pagination) is largely duplicated by the output schema, so beyond the no-side-effect note it adds limited new behavioral context.

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?

Two sentences, no filler: the input modes and the returned payload are front-loaded, and the read-only caveat closes it. Every clause earns its place.

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 16-parameter tool with full schema coverage, an output schema, and rich annotations, the description covers what the tool does, what it returns at a high level, and its non-persistent nature. The remaining gap is sibling disambiguation against the historical-metrics and forecast generators.

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 one of the 16 parameters is already documented in the schema. The description's 'up to 20 seed keywords' and mode list restate constraints already encoded as maxItems and mutually exclusive fields. Baseline 3 applies since the schema does the heavy lifting.

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?

States a specific verb and resource ('Discover Keyword Planner ideas') and enumerates the input modes (seed keywords, URL, keywords+URL, site). It clearly differs in kind from list/get siblings, though it never explicitly contrasts itself with the closely related google_ads_generate_keyword_historical_metrics, which also returns historical volume.

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 usage by listing the four seed-source modes, and notes the read-only/no-plan-saved constraint. However it gives no explicit 'use this when...' guidance and does not route the agent between this tool, generate_keyword_historical_metrics, and generate_keyword_forecast_metrics, all of which overlap on metrics.

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

Deploy Server