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

ghl-mcp-server-v2

by zackscriven

ghl_ad_fb_pixel_list

Read-onlyIdempotent

Retrieves Facebook conversion pixels for a location, with optional pagination, field projection, and channel selection for Facebook or Instagram datasets.

Instructions

Get conversion pixels Retrieve Facebook conversion pixels for a location. channel selects between two unrelated behaviours. For FACEBOOK (the default) the response is { items, total }, or a paginated { items, paging } envelope when limit (max 100) is given — pass after from paging.next for the next batch — and projection (comma-separated, from createdAt, fbIsCrmPixel, fbPixelCode, fbPixelId, name, type) narrows each item. For IG the response is instead a bare array of Instagram datasets carrying only an id, and limit, after, and projection are ignored. Endpoint: GET /ad-publishing/facebook/pixels (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>"
    },
    "name": "ghl_ad_fb_pixel_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
afterNoOpaque cursor for the next batch, taken from the previous response paging.next
limitNoPage size for a paginated fetch (max 100, FACEBOOK channel only). When set, the response is a { items, paging } envelope instead of { items, total }.
pageIdNoFacebook page ID
channelNoChannel type
igUserIdNoInstagram user ID
locationIdYesLocation identifier
projectionNoFields to return on each item, comma-separated (e.g. ?projection=name,fbPixelId). When set, only the requested fields are returned. Selectable fields: createdAt, fbIsCrmPixel, fbPixelCode, fbPixelId, name, type — any other value is rejected. Omit the param entirely to receive the full item as-is.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 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 / channel / enum
      Added value: +[
      +  "IG",
      +  "FACEBOOK"
      +]
    • addedInput schema / properties / limit
      Added value: +{
      +  "description": "Page size for a paginated fetch (max 100, FACEBOOK channel only). When set, the response is a { items, paging } envelope instead of { items, total }.",
      +  "example": "25",
      +  "type": "string"
      +}
    • addedInput schema / properties / projection
      Added value: +{
      +  "description": "Fields to return on each item, comma-separated (e.g. ?projection=name,fbPixelId). When set, only the requested fields are returned. Selectable fields: createdAt, fbIsCrmPixel, fbPixelCode, fbPixelId, name, type — any other value is rejected. Omit the param entirely to receive the full item as-is.",
      +  "example": [
      +    "fbIsCrmPixel",
      +    "fbPixelCode"
      +  ],
      +  "items": {
      +    "enum": [
      +      "createdAt",
      +      "fbIsCrmPixel",
      +      "fbPixelCode",
      +      "fbPixelId",
      +      "name",
      +      "type"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  2. First observedv2.0.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=true and idempotentHint=true; the description goes well beyond by disclosing the two divergent response shapes (`{ items, total }` vs `{ items, paging }`), that limit triggers the envelope, and that IG returns a bare array ignoring limit/after/projection. This is exactly the kind of context annotations cannot convey.

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?

Front-loads purpose, then the channel behaviour, then endpoint metadata in order of importance; every sentence carries information. It is somewhat dense but no sentence is wasted; the trailing 'Pagination params' line is slightly redundant after the earlier pagination explanation.

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?

There is no output schema, yet the description fully documents return shapes for both channels plus pagination and projection semantics, and adds endpoint/scope metadata. An agent has everything needed to call and interpret the result correctly.

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

Parameters4/5

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

Schema coverage is 100%, so individual params are already documented, but the description adds cross-parameter meaning: that `channel` switches unrelated behaviours and that `limit`/`after`/`projection` are ignored on IG. Slightly redundant on the projection field list, but the interaction semantics add genuine value beyond the schema.

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+resource ('Retrieve Facebook conversion pixels for a location') and clarifies scope via the `channel` distinction between two distinct behaviours. An agent can distinguish this list operation from the sibling `ghl_ad_fb_pixel_upsert` without opening the schema.

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?

Explains when `limit` triggers pagination ('pass `after` from `paging.next` for the next batch') and when `projection` applies, giving clear behavioral context for correct invocation. However, it doesn't explicitly name a sibling alternative or state when-not-to-use (e.g., vs upsert), leaving some routing inference to the agent.

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