AdsAgent — Google Ads MCP

google_ads_pmax_create_prepare

Prepare one atomic, paused standard Performance Max campaign using existing account image assets. location_ids and language_ids are required; without them the answer is needs_input, never a worldwide campaign. The approval summary lists locations, exclusions, geo option (default PRESENCE) and languages.

Input Schema

TableJSON Schema

Name	Required	Description
`retail`	No
`headlines`	Yes
`final_urls`	Yes
`customer_id`	Yes	10-digit Google Ads customer id.
`logo_assets`	Yes
`target_roas`	No
`descriptions`	Yes
`language_ids`	No	language_constant ids. Required; there is no implicit all-languages default.
`location_ids`	No	geo_target_constant ids (country, region or city) to target. Required; resolve names with google_ads_geo_targets_suggest.
`budget_micros`	Yes
`business_name`	Yes
`campaign_name`	Yes
`search_themes`	No
`long_headlines`	Yes
`audience_signal`	No
`geo_target_type`	No	Defaults to PRESENCE (only people in the location).
`asset_group_name`	Yes
`bidding_strategy`	Yes
`targeting_source`	No	Where the targeting came from; shown in the approval summary. Defaults to user.
`target_cpa_micros`	No
`connection_context`	No
`excluded_location_ids`	No	geo_target_constant ids to exclude.
`marketing_image_assets`	Yes
`square_marketing_image_assets`	Yes
`contains_eu_political_advertising`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 16, 2026

addedInput schema / properties / excluded_location_ids

Added value: +{
+  "description": "geo_target_constant ids to exclude.",
+  "items": {
+    "pattern": "^[1-9][0-9]*$",
+    "type": "string"
+  },
+  "maxItems": 100,
+  "type": "array",
+  "uniqueItems": true
+}

addedInput schema / properties / geo_target_type

Added value: +{
+  "description": "Defaults to PRESENCE (only people in the location).",
+  "enum": [
+    "PRESENCE",
+    "PRESENCE_OR_INTEREST"
+  ]
+}

addedInput schema / properties / language_ids

Added value: +{
+  "description": "language_constant ids. Required; there is no implicit all-languages default.",
+  "items": {
+    "pattern": "^[1-9][0-9]*$",
+    "type": "string"
+  },
+  "maxItems": 50,
+  "minItems": 1,
+  "type": "array",
+  "uniqueItems": true
+}

addedInput schema / properties / location_ids

Added value: +{
+  "description": "geo_target_constant ids (country, region or city) to target. Required; resolve names with google_ads_geo_targets_suggest.",
+  "items": {
+    "pattern": "^[1-9][0-9]*$",
+    "type": "string"
+  },
+  "maxItems": 100,
+  "minItems": 1,
+  "type": "array",
+  "uniqueItems": true
+}

addedInput schema / properties / targeting_source

Added value: +{
+  "description": "Where the targeting came from; shown in the approval summary. Defaults to user.",
+  "enum": [
+    "user",
+    "template",
+    "source_campaign"
+  ]
+}

Changed1 schema field changedOct 13, 2026
- addedInput schema / properties / connection_context
```
Added value: +{
+  "pattern": "^mctx_v1_[0-9a-f]{64}$",
+  "type": "string"
+}
```

Changed3 schema fields changedOct 4, 2026

addedInput schema / properties / audience_signal

Added value: +{
+  "pattern": "^customers/[0-9]+/audiences/[1-9][0-9]*$",
+  "type": "string"
+}

addedInput schema / properties / retail

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "feed_label": {
+      "pattern": "^[A-Z0-9_-]{1,20}$",
+      "type": "string"
+    },
+    "listing_tree": {
+      "oneOf": [
+        {
+          "additionalProperties": false,
+          "properties": {
+            "include": {
+              "type": "boolean"
+            }
+          },
+          "required": [
+            "include"
+          ],
+          "type": "object"
+        },
+        {
+          "additionalProperties": false,
+          "properties": {
+            "children": {
+              "items": {
+                "additionalProperties": false,
+                "properties": {
+                  "node": {
+                    "oneOf": [
+                      {
+                        "additionalProperties": false,
+                        "properties": {
+                          "include": {
+                            "type": "boolean"
+                          }
+                        },
+                        "required": [
+                          "include"
+                        ],
+                        "type": "object"
+                      },
+                      {
+                        "additionalProperties": false,
+                        "properties": {
+                          "children": {
+                            "items": {
+                              "additionalProperties": false,
+                              "properties": {
+                                "node": {
+                                  "additionalProperties": false,
+                                  "properties": {
+                                    "include": {
+                                      "type": "boolean"
+                                    }
+                                  },
+                                  "required": [
+                                    "include"
+                                  ],
+                                  "type": "object"
+                                },
+                                "value": {
+                                  "maxLength": 150,
+                                  "minLength": 1,
+                                  "type": [
+                                    "string",
+                                    "null"
+                                  ]
+                                }
+                              },
+                              "required": [
+                                "value",
+                                "node"
+                              ],
+                              "type": "object"
+                            },
+                            "maxItems": 50,
+                            "minItems": 2,
+                            "type": "array"
+                          },
+                          "dimension": {
+                            "enum": [
+                              "brand",
+                              "item_id"
+                            ]
+                          }
+                        },
+                        "required": [
+                          "dimension",
+                          "children"
+                        ],
+                        "type": "object"
+                      }
+                    ]
+                  },
+                  "value": {
+                    "maxLength": 150,
+                    "minLength": 1,
+                    "type": [
+                      "string",
+                      "null"
+                    ]
+                  }
+                },
+                "required": [
+                  "value",
+                  "node"
+                ],
+                "type": "object"
+              },
+              "maxItems": 50,
+              "minItems": 2,
+              "type": "array"
+            },
+            "dimension": {
+              "enum": [
+                "brand",
+                "item_id"
+              ]
+            }
+          },
+          "required": [
+            "dimension",
+            "children"
+          ],
+          "type": "object"
+        }
+      ]
+    },
+    "merchant_id": {
+      "pattern": "^[1-9][0-9]*$",
+      "type": "string"
+    }
+  },
+  "required": [
+    "merchant_id",
+    "feed_label",
+    "listing_tree"
+  ],
+  "type": "object"
+}

addedInput schema / properties / search_themes

Added value: +{
+  "items": {
+    "maxLength": 80,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 25,
+  "type": "array",
+  "uniqueItems": true
+}

First observedSep 16, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations only declare readOnlyHint=false/destructiveHint=false. The description adds substantive behavior: the campaign is created paused, it is an atomic operation, it uses existing account image assets, it returns needs_input on missing targeting, and it enumerates what the approval summary will contain. No auth or rate-limit context, but well beyond the annotations.

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?

Three sentences, front-loaded with the core action, then the targeting constraint, then the approval-summary contents. No filler and every sentence carries distinct information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description must carry more weight. It covers the critical gating behavior and approval summary, but for a 25-parameter tool with nested objects and 14 required fields, it omits guidance on the asset, bidding, budget and retail inputs. Adequate but incomplete for the complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 24% across 25 params (14 required, plus a nested retail object). The description only touches location_ids, language_ids, geo option and exclusions, all of which already carry schema descriptions. The 19 remaining parameters (headlines, assets, bidding, retail tree, etc.) get no semantic help, so the description does not compensate for the coverage gap.

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 gives a precise verb+resource: 'Prepare one atomic, paused standard Performance Max campaign.' The qualifiers (atomic, paused, standard) and the prepare-vs-confirm naming distinguish it from the sibling google_ads_pmax_create_confirm 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 Guidelines4/5

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

It states an explicit when-not rule: without location_ids and language_ids the response is needs_input, 'never a worldwide campaign.' That is strong conditional guidance, but it never explicitly names the confirm sibling or the required prepare-then-approve workflow, so the alternative routing is left implicit.

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

All AdsAgent — Google Ads 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?