adAuditListReturns paginated saved private ad reviews with stable IDs and current job states. Saved reviews remain readable while new processing is unavailable.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| cursor | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Output schema / oneOfPrevious value: -[
- {
- "additionalProperties": false,
- "properties": {
- "ok": {
- "const": true,
- "type": "boolean"
- },
- "output": {
- "additionalProperties": false,
- "properties": {
- "cursor": {
- "anyOf": [
- {
- "maxLength": 4096,
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "done": {
- "type": "boolean"
- },
- "items": {
- "items": {
- "$ref": "#/$defs/__schema0"
- },
- "maxItems": 20,
- "type": "array"
- },
- "reviewPath": {
- "const": "/app/iq/meta-ads/audit",
- "type": "string"
- }
- },
- "required": [
- "cursor",
- "done",
- "items",
- "reviewPath"
- ],
- "type": "object"
- },
- "toolName": {
- "const": "adAuditList",
- "type": "string"
- }
- },
- "required": [
- "ok",
- "output",
- "toolName"
- ],
- "type": "object"
- },
- {
- "additionalProperties": false,
- "properties": {
- "error": {
- "additionalProperties": false,
- "properties": {
- "code": {
- "enum": [
- "INVALID_INPUT",
- "FORBIDDEN",
- "NOT_FOUND",
- "CONFLICT",
- "FEATURE_DISABLED",
- "CONFIRMATION_REQUIRED",
- "CONFIRMATION_INVALID",
- "UPSTREAM_FAILED",
- "NEEDS_REVIEW",
- "INTERNAL"
- ],
- "type": "string"
- },
- "message": {
- "maxLength": 2048,
- "minLength": 1,
- "type": "string"
- },
- "retryable": {
- "type": "boolean"
- }
- },
- "required": [
- "code",
- "message",
- "retryable"
- ],
- "type": "object"
- },
- "ok": {
- "const": false,
- "type": "boolean"
- },
- "toolName": {
- "const": "adAuditList",
- "type": "string"
- }
- },
- "required": [
- "error",
- "ok",
- "toolName"
- ],
- "type": "object"
- }
-]New value: +[
+ {
+ "additionalProperties": false,
+ "properties": {
+ "ok": {
+ "const": true,
+ "type": "boolean"
+ },
+ "output": {
+ "additionalProperties": false,
+ "properties": {
+ "cursor": {
+ "anyOf": [
+ {
+ "maxLength": 4096,
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "done": {
+ "type": "boolean"
+ },
+ "items": {
+ "items": {
+ "$ref": "#/$defs/__schema0"
+ },
+ "maxItems": 20,
+ "type": "array"
+ },
+ "reviewPath": {
+ "const": "/app/iq/meta-ads/audit",
+ "type": "string"
+ }
+ },
+ "required": [
+ "cursor",
+ "done",
+ "items",
+ "reviewPath"
+ ],
+ "type": "object"
+ },
+ "toolName": {
+ "const": "adAuditList",
+ "type": "string"
+ }
+ },
+ "required": [
+ "ok",
+ "output",
+ "toolName"
+ ],
+ "type": "object"
+ },
+ {
+ "additionalProperties": false,
+ "properties": {
+ "error": {
+ "additionalProperties": false,
+ "properties": {
+ "code": {
+ "enum": [
+ "AI_SCHEDULING_LIMIT_REACHED",
+ "AI_SCHEDULING_UNAVAILABLE",
+ "INVALID_INPUT",
+ "FORBIDDEN",
+ "NOT_FOUND",
+ "CONFLICT",
+ "FEATURE_DISABLED",
+ "CONFIRMATION_REQUIRED",
+ "CONFIRMATION_INVALID",
+ "UPSTREAM_FAILED",
+ "NEEDS_REVIEW",
+ "INTERNAL"
+ ],
+ "type": "string"
+ },
+ "message": {
+ "maxLength": 2048,
+ "minLength": 1,
+ "type": "string"
+ },
+ "retryable": {
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "code",
+ "message",
+ "retryable"
+ ],
+ "type": "object"
+ },
+ "ok": {
+ "const": false,
+ "type": "boolean"
+ },
+ "toolName": {
+ "const": "adAuditList",
+ "type": "string"
+ }
+ },
+ "required": [
+ "error",
+ "ok",
+ "toolName"
+ ],
+ "type": "object"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds real value beyond that: pagination, stable IDs, current job states, and the constraint that saved reviews stay readable during processing outages.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences that front-load what is returned and follow with the only non-obvious operational caveat. No filler or restated title content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a read-only list tool with two optional pagination params and an output schema that covers return values, the description is nearly sufficient. The remaining gap is that it does not point to adAuditGet for retrieving a single review.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must carry the load. 'Paginated' hints at the limit/cursor pair, but it never explains the 1-20 limit bound or the cursor semantics, leaving the two optional parameters largely undocumented in both places.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Returns paginated saved private ad reviews') plus the notable payload contents (stable IDs, current job states). It is implicitly distinct from the singular sibling adAuditGet, but the description never explicitly names that alternative, so the differentiation is left to inference.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied by the availability note ('Saved reviews remain readable while new processing is unavailable'), which tells the agent the tool still works when processing is down. However, there is no explicit when-to-use statement and no routing to adAuditGet for fetching an individual review.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.