AdsAgent — Meta Ads MCP

operations_confirm_entity_update

DestructiveIdempotent

Run the change the user just confirmed in this conversation: set the reviewed Meta entity fields from current to approved values. Requires approval_ref and expected_plan_digest. Batch approvals also require the complete expected_changes, including excluded rows

Input Schema

Name	Required	Description
`currency`	No	Account currency code shown in the approval.
`new_value`	No
`old_value`	No
`approval_ref`	Yes
`entity_count`	No	Number of accepted execution targets. Excluded rows are not counted.
`entity_names`	No	Accepted entity names in the same order as the complete reviewed batch.
`excluded_count`	No	Number of excluded rows in the complete reviewed batch.
`expected_changes`	No
`expected_plan_digest`	Yes

Output Schema

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

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 23, 2026

removedInput schema / properties / connection_context

Removed value: -{
-  "pattern": "^mctx_v1_[0-9a-f]{64}$",
-  "type": "string"
-}

addedInput schema / properties / currency

Added value: +{
+  "description": "Account currency code shown in the approval.",
+  "type": "string"
+}

addedInput schema / properties / entity_count

Added value: +{
+  "description": "Number of accepted execution targets. Excluded rows are not counted.",
+  "minimum": 0,
+  "type": "integer"
+}

addedInput schema / properties / entity_names

Added value: +{
+  "description": "Accepted entity names in the same order as the complete reviewed batch.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / excluded_count

Added value: +{
+  "description": "Number of excluded rows in the complete reviewed batch.",
+  "minimum": 0,
+  "type": "integer"
+}

addedInput schema / properties / new_value

Added value: +{
+  "type": [
+    "string",
+    "number",
+    "boolean",
+    "object",
+    "array"
+  ]
+}

addedInput schema / properties / old_value

Added value: +{
+  "type": [
+    "string",
+    "number",
+    "boolean",
+    "object",
+    "array",
+    "null"
+  ]
+}

Changed3 schema fields changedOct 18, 2026

changedInput schema / properties / approval_ref / maxLength
```
Previous value: -25New value: +38
```

changedInput schema / properties / approval_ref / pattern

Previous value: -"^appr_[0-9a-f]{20}$"New value: +"^(?:appr_[0-9a-f]{20}|batch_[0-9a-f]{32})$"

addedInput schema / properties / expected_changes

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

AddedOct 18, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, readOnlyHint=false, so the safety profile is covered. The description adds genuine value with the approval_ref/digest guards and the batch-completeness rule ('including excluded rows'), but does not disclose failure behavior on digest mismatch or what specifically gets overwritten.

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?

Three sentences, front-loaded with the action, then prerequisites, then the batch edge case. No filler; each sentence carries a distinct constraint.

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?

With an output schema present and strong annotations, the description need not explain returns. But for a destructive mutation it leaves gaps: the relationship to the prepare step, failure/mismatch behavior, and the semantics of the arbitrary old_value/new_value fields are unaddressed given 44% schema coverage.

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

Parameters3/5

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

Schema coverage is 44% and fully undocumented parameters (new_value, old_value, expected_changes) remain. The description compensates partially by spelling out the required approval_ref/expected_plan_digest and the completeness semantics of expected_changes, but says nothing about how old_value/new_value are used in the update.

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?

States a specific action (execute the user-confirmed change) and resource (reviewed Meta entity fields moving from current to approved values). It's clearly a confirmation/execution tool, distinguished from prepare-style siblings by 'Run the change the user just confirmed.' It doesn't name the prepare/deny counterparts explicitly, but the purpose is unambiguous.

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?

Establishes the usage context ('the change the user just confirmed in this conversation') and states required parameters. However, it never names the prepare counterpart (entities_prepare_update) that must precede it, nor points to operations_deny_approval for the decline path, so the routing decision is left to inference.

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?