Skip to main content
Glama
ghl-mcp-server-v2

ghl-mcp-server-v2

by zackscriven

ghl_ad_fb_audience_list

Read-onlyIdempotent

Retrieve Facebook custom audiences for a location and ad account, filter by audience type, and paginate results or limit returned fields for inventory and campaign planning.

Instructions

Get custom audiences Retrieve Facebook custom audiences for a location. Without limit the response is a plain array. When limit is provided (max 100) the response is a paginated { customAudiences, paging } envelope; pass after (from paging.next) to fetch the next batch. By default each item is returned in full; pass projection (comma-separated, dot-notation for nested fields, e.g. ?projection=id,name,dataSource.type) to return only the requested fields — any value outside the known field set is rejected. Endpoint: GET /ad-publishing/facebook/custom-audience (Version header: v3; source: v3/ad-publishing-v3.json) OAuth scopes: adPublishing.readonly Pagination params: limit — pass them to page through full result sets.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "locationId": "<locationId>",
      "type": "<type>",
      "adAccountId": "<adAccountId>"
    },
    "name": "ghl_ad_fb_audience_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeYesAudience list type
afterNoOpaque cursor for the next batch, taken from the previous response paging.next
limitNoPage size for a paginated fetch (max 100). When set, the response is a { customAudiences, paging } envelope instead of a plain array.
sourceNoAudience data source
locationIdYesLocation identifier
projectionNoFields to return on each item, comma-separated (e.g. ?projection=id,name,dataSource.type). When set, only the requested fields are returned. Nested fields use dot-notation; naming a parent (e.g. dataSource) returns the whole nested object. Any value outside the known field set is rejected. Omit the param entirely to receive the full item as-is.
adAccountIdYesAd account identifier

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv2.1.0
    • addedInput schema / properties / after
      Added value: +{
      +  "description": "Opaque cursor for the next batch, taken from the previous response paging.next",
      +  "example": "QVFIU...",
      +  "type": "string"
      +}
    • addedInput schema / properties / limit
      Added value: +{
      +  "description": "Page size for a paginated fetch (max 100). When set, the response is a { customAudiences, paging } envelope instead of a plain array.",
      +  "example": "25",
      +  "type": "string"
      +}
    • addedInput schema / properties / projection
      Added value: +{
      +  "description": "Fields to return on each item, comma-separated (e.g. ?projection=id,name,dataSource.type). When set, only the requested fields are returned. Nested fields use dot-notation; naming a parent (e.g. dataSource) returns the whole nested object. Any value outside the known field set is rejected. Omit the param entirely to receive the full item as-is.",
      +  "example": [
      +    "id",
      +    "name",
      +    "dataSource.type",
      +    "deliveryStatus.code"
      +  ],
      +  "items": {
      +    "enum": [
      +      "id",
      +      "name",
      +      "description",
      +      "approximateCountLowerBound",
      +      "approximateCountUpperBound",
      +      "subtype",
      +      "timeCreated",
      +      "timeUpdated",
      +      "dataSource",
      +      "dataSource.type",
      +      "dataSource.subType",
      +      "dataSource.creationParams",
      +      "deliveryStatus",
      +      "deliveryStatus.code",
      +      "deliveryStatus.description",
      +      "operationStatus",
      +      "operationStatus.code",
      +      "operationStatus.description"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  2. First observedv2.0.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare the safe read-only profile, and the description adds genuinely new behavioral facts: the response shape changes based on `limit`, the page cap is 100, cursors come from `paging.next`, unknown projection fields are rejected, and the call requires the adPublishing.readonly OAuth scope. That is substantial disclosure for a tool with no output schema.

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?

The middle section, pagination and projection semantics, is dense and front-loaded with the most decision-relevant facts. Minor waste remains in the redundant 'Get custom audiences' restatement of the title and the awkward trailing 'Pagination params: limit — pass them to page through full result sets' line, which adds nothing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only list endpoint with full schema coverage, the definition covers everything an agent needs: scope/auth, paging contract, response shape switching, field projection rules, and the source endpoint spec. Nothing material for correct invocation is missing.

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 description coverage is 100% and the per-parameter descriptions already document `limit`, `after`, `projection`, and the enums in detail, so the description largely restates them. It adds marginal value only in showing the `?projection=id,name,dataSource.type` query syntax; the `type` and `source` enums are never explained in prose.

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?

States a specific verb and resource ('Retrieve Facebook custom audiences for a location'), which distinguishes it cleanly from the sibling ghl_ad_fb_audience_get (single audience) and the member-management siblings. An agent knows immediately what it gets and at what scope.

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?

Gives clear operational guidance: omit `limit` for a plain array, supply it for a paginated envelope, use `after` to continue, and use `projection` to narrow fields. It stops short of naming alternatives such as ghl_ad_fb_audience_get when a single audience is wanted, so routing is implied rather than explicit.

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

Deploy Server

Other Tools