AdsAgent — Meta Ads MCP

tasks_cancel

Destructive

Cancel a pending tenant-owned task or stop its remaining ordinary Insights recovery while preserving terminal history

Input Schema

Name	Required	Description	Default
`task_ref`	No

Output Schema

Name	Required	Description	Default
`message`	No
`retryable`	No
`support_ref`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 23, 2026
- removedInput schema / properties / connection_context
```
Removed value: -{
-  "pattern": "^mctx_v1_[0-9a-f]{64}$",
-  "type": "string"
-}
```

Changed16 schema fields changedOct 22, 2026

removedOutput schema / $defs

Removed value: -{
-  "s0": {
-    "properties": {
-      "ad_count": {
-        "type": "integer"
-      },
-      "ads_per_adset": {
-        "type": "integer"
-      },
-      "adset_count": {
-        "type": "integer"
-      },
-      "adsets_per_campaign": {
-        "type": "integer"
-      },
-      "campaign_count": {
-        "type": "integer"
-      }
-    },
-    "type": "object"
-  },
-  "s1": {
-    "properties": {
-      "arguments": {
-        "properties": {
-          "mutation_ref": {
-            "type": "string"
-          },
-          "response_mode": {
-            "type": "string"
-          },
-          "task_ref": {
-            "type": "string"
-          }
-        },
-        "type": "object"
-      },
-      "instruction": {
-        "type": "string"
-      },
-      "name": {
-        "type": "string"
-      },
-      "tool": {
-        "type": "string"
-      },
-      "type": {
-        "type": "string"
-      }
-    },
-    "type": [
-      "null",
-      "object",
-      "string"
-    ]
-  }
-}

changedOutput schema / else / else / anyOf

Previous value: -[
-  {
-    "properties": {
-      "status": {
-        "const": "cancelled"
-      }
-    }
-  },
-  {
-    "properties": {
-      "recovery_cancelled": {
-        "const": true
-      },
-      "status": {
-        "enum": [
-          "completed",
-          "partial_completed",
-          "failed"
-        ]
-      }
-    },
-    "required": [
-      "recovery_cancelled"
-    ]
-  }
-]New value: +[
+  {
+    "properties": {
+      "status": {
+        "const": "cancelled"
+      }
+    },
+    "required": [
+      "status",
+      "task_type",
+      "terminal"
+    ]
+  },
+  {
+    "properties": {
+      "recovery_cancelled": {
+        "const": true
+      }
+    },
+    "required": [
+      "recovery_cancelled",
+      "status",
+      "task_type",
+      "terminal"
+    ]
+  }
+]

removedOutput schema / else / else / properties / execution_summary / properties / created / $ref
```
Removed value: -"#/$defs/s0"
```

addedOutput schema / else / else / properties / execution_summary / properties / created / properties

Added value: +{
+  "ad_count": {
+    "type": "integer"
+  },
+  "ads_per_adset": {
+    "type": "integer"
+  },
+  "adset_count": {
+    "type": "integer"
+  },
+  "adsets_per_campaign": {
+    "type": "integer"
+  },
+  "campaign_count": {
+    "type": "integer"
+  }
+}

addedOutput schema / else / else / properties / execution_summary / properties / created / type
```
Added value: +"object"
```
removedOutput schema / else / else / properties / execution_summary / properties / failures / properties / items / items / properties / next_action / $ref
```
Removed value: -"#/$defs/s1"
```

added

Output schema / else / else / properties / execution_summary / properties / failures / properties / items / items / properties / next_action / properties

Added value: +{
+  "arguments": {
+    "properties": {
+      "mutation_ref": {
+        "type": "string"
+      },
+      "response_mode": {
+        "type": "string"
+      },
+      "task_ref": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "instruction": {
+    "type": "string"
+  },
+  "name": {
+    "type": "string"
+  },
+  "tool": {
+    "type": "string"
+  },
+  "type": {
+    "type": "string"
+  }
+}

addedOutput schema / else / else / properties / execution_summary / properties / failures / properties / items / items / properties / next_action / type
```
Added value: +[
+  "null",
+  "object",
+  "string"
+]
```
removedOutput schema / else / else / properties / execution_summary / properties / planned / $ref
```
Removed value: -"#/$defs/s0"
```

addedOutput schema / else / else / properties / execution_summary / properties / planned / properties

Added value: +{
+  "ad_count": {
+    "type": "integer"
+  },
+  "ads_per_adset": {
+    "type": "integer"
+  },
+  "adset_count": {
+    "type": "integer"
+  },
+  "adsets_per_campaign": {
+    "type": "integer"
+  },
+  "campaign_count": {
+    "type": "integer"
+  }
+}

addedOutput schema / else / else / properties / execution_summary / properties / planned / type
```
Added value: +"object"
```
removedOutput schema / else / else / properties / next_action / $ref
```
Removed value: -"#/$defs/s1"
```

addedOutput schema / else / else / properties / next_action / properties

Added value: +{
+  "arguments": {
+    "properties": {
+      "mutation_ref": {
+        "type": "string"
+      },
+      "response_mode": {
+        "type": "string"
+      },
+      "task_ref": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "instruction": {
+    "type": "string"
+  },
+  "name": {
+    "type": "string"
+  },
+  "tool": {
+    "type": "string"
+  },
+  "type": {
+    "type": "string"
+  }
+}

addedOutput schema / else / else / properties / next_action / type
```
Added value: +[
+  "null",
+  "object",
+  "string"
+]
```
addedOutput schema / else / else / properties / recovery_cancelled
```
Added value: +{
+  "const": true
+}
```

addedOutput schema / else / else / properties / status

Added value: +{
+  "enum": [
+    "cancelled",
+    "completed",
+    "partial_completed",
+    "failed"
+  ]
+}

Changed6 schema fields changedOct 15, 2026
- addedOutput schema / else / then / properties / category
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / else / then / properties / expected
```
Added value: +{
+  "type": "boolean"
+}
```
- addedOutput schema / else / then / properties / failure_kind
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / else / then / properties / responsibility_hint
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / else / then / properties / route
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / else / then / properties / user_visible
```
Added value: +{
+  "type": "boolean"
+}
```
Changed1 schema field changedOct 13, 2026
- addedInput schema / properties / connection_context
```
Added value: +{
+  "pattern": "^mctx_v1_[0-9a-f]{64}$",
+  "type": "string"
+}
```
First observedSep 9, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation/safety profile is covered. The description adds useful scope context ('tenant-owned', 'pending only') and a non-destruction guarantee ('preserving terminal history'), but does not state irreversibility, required permissions, or what happens to in-flight work beyond the vague 'ordinary Insights recovery'.

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?

One front-loaded sentence with the verb and resource leading. Efficient, though 'ordinary Insights recovery' is compressed to the point of being hard to interpret.

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 need not be explained, and annotations cover the destructive profile. The gap is the lone parameter's format and the missing linkage to how an agent obtains a cancellable task reference; for a destructive mutation this leaves the invocation path partly unstated.

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 0% for the single parameter task_ref, and the description never mentions it. An agent gets no hint whether it expects an ID, a task name, or a reference from a sibling tool like tasks_latest — a real ambiguity when only one identifier is accepted.

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?

Names a specific verb (cancel) and a specific resource (task), plus the scope restriction to pending tenant-owned tasks. This distinguishes it reasonably from siblings like tasks_get_status or tasks_list, though the phrase 'ordinary Insights recovery' is opaque jargon that an agent may not parse.

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 word 'pending' implies a precondition (only pending tasks are cancellable) and the tool is implicitly the mutation counterpart to the tasks_* read siblings. However, no alternative is explicitly named, no guidance is given on what to do when a task is not pending, and no confirmation step is mentioned.

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

All AdsAgent — Meta 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?