AdsAgent — Google Ads MCP

mmp_delete_connection

Destructive

Delete one MMP connection on the Meta-owned MMP service. Destructive write; call only on explicit user request. Returns mmp_not_enabled while MMP is not enabled for the tenant.

Input Schema

Name	Required	Description	Default
`connection_id`	Yes
`connection_context`	No

Output Schema

Name	Required	Description	Default
`ok`	No
`code`	No
`rows`	No
`error`	No
`needs`	No
`reason`	No
`status`	No
`enabled`	No
`provider`	No
`retryable`	No
`truncated`	No
`error_code`	No
`total_rows`	No
`cohort_data`	No
`connections`	No
`next_action`	No
`next_cursor`	No
`support_ref`	No
`connection_id`	No
`oversized_row`	No
`invalid_fields`	No
`rejected_paths`	No
`origin_support_ref`	No
`metadata_by_connection`	No
`cohort_configs_by_connection`	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"
+    },
+    "cohort_configs_by_connection": {
+      "additionalProperties": true,
+      "properties": {},
+      "type": "object"
+    },
+    "cohort_data": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {},
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "connection_id": {
+      "type": "string"
+    },
+    "connections": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {},
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "enabled": {
+      "type": "boolean"
+    },
+    "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"
+    },
+    "invalid_fields": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "metadata_by_connection": {
+      "additionalProperties": true,
+      "properties": {},
+      "type": "object"
+    },
+    "needs": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "next_action": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "additionalProperties": true,
+              "properties": {},
+              "type": "object"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "next_cursor": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "ok": {
+      "type": "boolean"
+    },
+    "origin_support_ref": {
+      "type": "string"
+    },
+    "oversized_row": {
+      "type": "boolean"
+    },
+    "provider": {
+      "type": "string"
+    },
+    "reason": {
+      "type": "string"
+    },
+    "rejected_paths": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "retryable": {
+      "type": "boolean"
+    },
+    "rows": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {},
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "status": {
+      "type": "string"
+    },
+    "support_ref": {
+      "type": "string"
+    },
+    "total_rows": {
+      "type": "integer"
+    },
+    "truncated": {
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

AddedOct 18, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, so the description reinforces rather than duplicates. It adds valuable behavioral context by stating the tool returns 'mmp_not_enabled' when MMP is not enabled for the tenant, which is not covered by annotations. It does not describe what associated data might be lost beyond the connection itself, leaving a minor gap.

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 are tightly packed with purpose, usage constraint, and error condition, with the core action front-loaded. Every sentence adds distinct information without redundancy.

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?

Given the destructive nature and the presence of annotations and an output schema, the description covers the essential purpose, explicit-request requirement, and a key error state. It falls slightly short by not explaining the parameters or clarifying whether the deletion is irreversible or affects related data.

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?

The input schema has 0% description coverage, so the description must explain the two parameters (connection_id and connection_context). The description only implies that a connection is targeted, but never explains what connection_id represents or what connection_context is for, leaving an agent to infer from parameter names alone.

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 states a specific verb ('Delete') and resource ('one MMP connection on the Meta-owned MMP service'), making the operation unambiguous. It clearly distinguishes itself from sibling tools like mmp_get_state or mmp_refresh_connection by focusing on deletion.

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 provides a clear usage condition: 'call only on explicit user request,' which implicitly defines when not to use it. However, it does not name alternative tools or contrast with sibling operations, so it stops just short of a 5.

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?