AdsAgent — Google Ads MCP

google_ads_deep_analysis_export

Persist a single-use 10-minute download grant and return its CSV export URL for a bounded whitelisted deep-analysis query. No rows are returned in the MCP response.

Input Schema

Name	Required	Description
`limit`	No
`family`	Yes
`date_to`	Yes
`date_from`	Yes
`customer_id`	Yes	10-digit Google Ads customer id.
`connection_context`	No

Output Schema

Name	Required	Description	Default
`ok`	No
`code`	No
`error`	No
`needs`	No
`reason`	No
`status`	No
`filename`	No
`retryable`	No
`error_code`	No
`expires_at`	No
`next_action`	No
`support_ref`	No
`download_url`	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"
+    },
+    "download_url": {
+      "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"
+    },
+    "expires_at": {
+      "type": "string"
+    },
+    "filename": {
+      "type": "string"
+    },
+    "invalid_fields": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "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"
+    },
+    "status": {
+      "type": "string"
+    },
+    "support_ref": {
+      "type": "string"
+    }
+  },
+  "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

A3.7/5.0

Behavior5/5

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

Adds substantial context beyond annotations: the grant is single-use, expires in 10 minutes, and the MCP response deliberately contains no rows. These operational traits (ephemerality, one-shot consumption, empty payload) are exactly what an agent needs and are not derivable from readOnlyHint=false / destructiveHint=false.

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 tight sentences, front-loaded with the core action and followed by the critical caveat about return behavior. Nothing redundant.

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?

An output schema exists so return values needn't be explained, and the empty-payload behavior is covered. But for a tool with 4 required parameters and near-zero schema documentation, the description leaves family values, date format, and the grant lifecycle unaddressed.

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 description coverage is only 17% (only customer_id is documented), and the description supplies no per-parameter meaning. 'bounded whitelisted' gestures at the family/limit constraints but gives no valid values, date formats, or role for connection_context — a real gap for a 6-parameter tool.

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?

Specific verb+resource: persists a download grant and returns a CSV export URL for a deep-analysis query. It clearly is not the query tool itself ('no rows are returned'), which distinguishes it from google_ads_deep_analysis_query. It stops short of naming that sibling explicitly.

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?

Usage is only implicit: the phrase 'for a bounded whitelisted deep-analysis query' hints this is the export step of a deep-analysis workflow. It never states when to choose this over google_ads_deep_analysis_query, insights_query_consistent, or google_ads_query_preflight, nor any prerequisites.

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?