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

ghl-mcp-server-v2

by zackscriven

ghl_ad_fb_pixel_upsert

Idempotent

Creates a Facebook conversion pixel or renames an existing one by passing conversionPixelId; only renaming is supported for updates, and INSTAGRAM_DM renames are rejected.

Instructions

Upsert conversion pixel Create a Facebook conversion pixel, or rename an existing one by passing conversionPixelId. The two paths acknowledge differently: a create returns the new id, a rename returns only { success: true }. Renaming is the only update supported, and it rejects type: INSTAGRAM_DM. Creating an INSTAGRAM_DM dataset requires igUserId and fails if one already exists for that account. Endpoint: PUT /ad-publishing/facebook/pixels (Version header: v3; source: v3/ad-publishing-v3.json) OAuth scopes: adPublishing.write

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": {
      "body": "<body>"
    },
    "name": "ghl_ad_fb_pixel_upsert"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesRequest body (schema carried verbatim from the official OpenAPI spec).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.1.0
    • addedInput schema / properties / body / properties / type / enum
      Added value: +[
      +  "LEAD_EVENT",
      +  "FUNNEL_EVENT",
      +  "INSTAGRAM_DM"
      +]
    • addedInput schema / properties / body / title
      Added value: +"UpsertConversionPixelDTO"
  2. First observedv2.0.0

TDQS

A4.8/5.0
Behavior5/5

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

Goes well past the annotations: discloses the asymmetric response shapes ({new id} on create vs. {success: true} on rename), the failure mode for duplicate INSTAGRAM_DM datasets, the adPublishing.write OAuth scope, and the endpoint/version. These are exactly the surprises the agent needs warned about before calling.

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-loaded with the verb and both paths, then restrictions, then endpoint metadata. Dense but every sentence carries a rule an agent cannot infer. The trailing endpoint/scope lines are spec boilerplate but small enough not to hurt.

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 nested-body upsert with no output schema and a single top-level parameter, the description covers the branching logic, conditional requirements, rejection rules, response shape difference, and auth scope. Nothing needed to call it correctly is missing.

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 the baseline is 3; the description earns above baseline by explaining that conversionPixelId switches the tool from create to rename, and that igUserId is conditionally required for INSTAGRAM_DM. It doesn't cover name/locationId semantics, but those are already documented in 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 and resource ('Upsert conversion pixel') and immediately decomposes it into the two real behavioral paths: create, or rename via conversionPixelId. That distinguishes it from read-side siblings like ghl_ad_fb_pixel_list without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly defines when each path applies (create vs. rename), what is not allowed (renaming rejects type: INSTAGRAM_DM; rename is the only supported update), and the precondition for INSTAGRAM_DM creation (igUserId required, fails if one already exists for the account). The selection logic is fully specified.

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