AdsAgent — Google Ads MCP

google_ads_deep_analysis_query

Read-only

Run a whitelisted deep-analysis query for one customer.

Input Schema

Name	Required	Description	Default
`limit`	No
`family`	Yes
`date_to`	Yes
`date_from`	Yes
`customer_id`	Yes	10-digit Google Ads customer id.
`detail_level`	No	summary returns totals plus at most 20 top rows; rows explicitly returns at most 200 rows.	summary
`connection_context`	No

Output Schema

Name	Required	Description	Default
`ok`	No
`code`	No
`meta`	No
`rows`	No
`error`	No
`needs`	No
`family`	No
`reason`	No
`date_to`	No
`summary`	No
`top_rows`	No
`date_from`	No
`retryable`	No
`error_code`	No
`customer_id`	No
`next_action`	No
`support_ref`	No
`invalid_fields`	No
`rejected_paths`	No
`origin_support_ref`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 28, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "code": {
+      "type": "string"
+    },
+    "customer_id": {
+      "type": "string"
+    },
+    "date_from": {
+      "type": "string"
+    },
+    "date_to": {
+      "type": "string"
+    },
+    "error": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "additionalProperties": true,
+              "properties": {
+                "code": {
+                  "type": "string"
+                },
+                "details": {
+                  "additionalProperties": true,
+                  "properties": {},
+                  "type": "object"
+                },
+                "message": {
+                  "type": "string"
+                },
+                "retryable": {
+                  "type": "boolean"
+                },
+                "support_ref": {
+                  "type": "string"
+                }
+              },
+              "type": "object"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "error_code": {
+      "type": "string"
+    },
+    "family": {
+      "type": "string"
+    },
+    "invalid_fields": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "meta": {
+      "additionalProperties": true,
+      "properties": {
+        "complete": {
+          "type": "boolean"
+        },
+        "has_more": {
+          "type": "boolean"
+        },
+        "limit": {
+          "type": "integer"
+        },
+        "next_continuation": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "next_cursor": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "pagination_complete": {
+          "type": "boolean"
+        },
+        "returned_count": {
+          "type": "integer"
+        },
+        "source": {
+          "type": "string"
+        },
+        "total_count": {
+          "anyOf": [
+            {
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "truncated": {
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "needs": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "next_action": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "additionalProperties": true,
+              "properties": {},
+              "type": "object"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "ok": {
+      "type": "boolean"
+    },
+    "origin_support_ref": {
+      "type": "string"
+    },
+    "reason": {
+      "type": "string"
+    },
+    "rejected_paths": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "retryable": {
+      "type": "boolean"
+    },
+    "rows": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {},
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "summary": {
+      "additionalProperties": true,
+      "properties": {},
+      "type": "object"
+    },
+    "support_ref": {
+      "type": "string"
+    },
+    "top_rows": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {},
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedOct 13, 2026
- addedInput schema / properties / connection_context
```
Added value: +{
+  "pattern": "^mctx_v1_[0-9a-f]{64}$",
+  "type": "string"
+}
```
First observedSep 16, 2026

TDQS

C2.5/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, non-destructive and closed-world behavior. The description adds only that the query is 'whitelisted' and scoped to one customer, but it does not explain what the whitelist covers, what happens with an invalid family, or how connection_context affects access.

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 description is a single front-loaded sentence with no filler. Its brevity is efficient, though it is arguably too terse for the tool's parameter complexity.

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

Completeness2/5

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

This is a seven-parameter analytical query tool with only 29% schema description coverage. The description does not explain the whitelist of families, date formats, limit behavior, or connection_context, leaving important calling details undocumented even though an output schema exists.

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

Parameters1/5

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

Schema description coverage is only 29%, so the description needs to compensate for undocumented parameters. It adds nothing meaningful about the required family, date_from, date_to, optional limit, or connection_context parameters; only 'one customer' loosely echoes customer_id.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a verb ('Run') and resource ('deep-analysis query') and scopes it to one customer. However, 'deep-analysis' largely restates the tool name, and the description does not clarify what a deep-analysis family is or how this differs from siblings such as google_ads_insights_query_daily or google_ads_deep_analysis_export.

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

Usage Guidelines2/5

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

There is no guidance on when to use this tool versus alternatives. It does not mention google_ads_analysis_families_list for discovering families, google_ads_query_preflight, google_ads_deep_analysis_export, or any prerequisite or exclusion.

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?