AdsAgent — Meta Ads MCP

mmp_insights_query_product_cohort

Read-only

Read cohorts; channel_pid required

Input Schema

Name	Required	Description	Default
`cursor`	No
`date_to`	Yes
`date_from`	Yes
`event_keys`	No
`channel_pid`	Yes
`cohort_days`	No
`product_ref`	No
`product_name`	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"
-}
```

Changed2 schema fields changedOct 18, 2026

addedInput schema / properties / cohort_days

Added value: +{
+  "items": {
+    "type": "integer"
+  },
+  "type": "array"
+}

addedInput schema / properties / cursor
```
Added value: +{
+  "type": "string"
+}
```

Changed6 schema fields changedOct 15, 2026
- addedOutput schema / then / properties / category
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / then / properties / expected
```
Added value: +{
+  "type": "boolean"
+}
```
- addedOutput schema / then / properties / failure_kind
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / then / properties / responsibility_hint
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / then / properties / route
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / 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"
+}
```

Changed2 schema fields changedSep 11, 2026

addedOutput schema / $defs / sa

Added value: +{
+  "properties": {
+    "can_report_stored_total": {
+      "type": "boolean"
+    },
+    "reason": {
+      "type": "string"
+    },
+    "zero_proven": {
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "can_report_stored_total",
+    "zero_proven",
+    "reason"
+  ],
+  "type": "object"
+}

addedOutput schema / else / properties / read_evidence

Added value: +{
+  "description": "Proofs apply independently to returned metrics and scope as stored/observed. A new read_ref is a call identifier, never a source watermark. False or missing proof means unknown, not zero. Fingerprints correlate requests/results in audits; they are not authorization or pagination tokens.",
+  "properties": {
+    "artifact_returned": {
+      "type": "boolean"
+    },
+    "configuration": {
+      "properties": {
+        "account_inventory_enumerated": {
+          "const": false
+        },
+        "all_campaigns_paused_proven": {
+          "const": false
+        },
+        "requested_ids_complete": {
+          "type": "boolean"
+        },
+        "scope": {
+          "const": "requested_entity_ids_only"
+        }
+      },
+      "type": "object"
+    },
+    "mmp": {
+      "properties": {
+        "can_report_scoped_totals": {
+          "type": "boolean"
+        },
+        "provider_cache_max_age_seconds": {
+          "const": 90
+        },
+        "reason": {
+          "type": "string"
+        },
+        "scope": {
+          "const": "linked_apps_queried_channels_and_windows"
+        },
+        "source_observed_at": {
+          "type": "null"
+        }
+      },
+      "type": "object"
+    },
+    "read_ref": {
+      "pattern": "^read_[0-9a-f]{32}$",
+      "type": "string"
+    },
+    "request_fingerprint": {
+      "type": "string"
+    },
+    "result_fingerprint": {
+      "type": "string"
+    },
+    "scopes": {
+      "items": {
+        "properties": {
+          "all_campaigns_paused_proven": {
+            "const": false
+          },
+          "funnel": {
+            "additionalProperties": {
+              "$ref": "#/$defs/sa"
+            },
+            "maxProperties": 32,
+            "type": "object"
+          },
+          "index": {
+            "type": "integer"
+          },
+          "inventory_anchor": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "inventory_coverage": {
+            "type": "string"
+          },
+          "inventory_source_observed_at": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "metrics": {
+            "additionalProperties": {
+              "$ref": "#/$defs/sa"
+            },
+            "type": "object"
+          },
+          "metrics_source_observed_at": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "range_complete": {
+            "type": [
+              "boolean",
+              "null"
+            ]
+          },
+          "scope": {
+            "const": "stored_query"
+          }
+        },
+        "type": "object"
+      },
+      "maxItems": 10,
+      "type": "array"
+    }
+  },
+  "required": [
+    "read_ref",
+    "request_fingerprint",
+    "result_fingerprint"
+  ],
+  "type": "object"
+}

First observedSep 9, 2026

TDQS

C2.1/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and closed-world scope, so the description adds nothing on safety. It stays silent on what cohort rows look like, how cursor paging behaves, or how cohort_days affects the output, which is exactly the context annotations can't give.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two clauses, zero waste, and the constraint is front-loaded after the verb. Brevity here is under-specification rather than efficiency, capping the score at adequate.

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?

With 8 parameters, 0% schema descriptions, and an output schema present, the description does almost none of the work needed to call this correctly; cohort semantics and date/cohort_days interactions are entirely missing.

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 0% across 8 parameters, and the description only mentions channel_pid, which is already listed as required in the schema. date_from/date_to format, cohort_days meaning, event_keys, product_ref vs product_name, and cursor usage are all undocumented.

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

Purpose2/5

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

The text "Read cohorts" essentially restates the tool name (mmp_insights_query_product_cohort) without specifying what a "cohort" means here or how it differs from siblings like mmp_insights_query_product_event_summary. Only the bare read verb adds information.

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?

"channel_pid required" is a prerequisite, not usage guidance; there is no statement of when to pick this over the event-summary or today tools. The agent is left to infer selection context from the name alone.

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?