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

ghl-mcp-server-v2

by zackscriven

ghl_ad_fb_targeting_search

Read-onlyIdempotent

Search Facebook ad targeting options to build ad set audiences, including geolocations, interests, behaviors, demographics, and languages. Use a query and targeting type to retrieve matching audience criteria.

Instructions

Search targeting options Search Facebook targeting options for ad set audience building. type selects which taxonomy is searched and determines the response shape: geolocation returns places, interest returns interests, behaviours, and demographics, and language returns locales. Geolocation and interest results are passed through from Facebook, so their fields are snake_case. Endpoint: GET /ad-publishing/facebook/targeting/search (Version header: v3; source: v3/ad-publishing-v3.json) OAuth scopes: adPublishing.readonly

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": {
      "type": "<type>",
      "query": "<query>"
    },
    "name": "ghl_ad_fb_targeting_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeYesTargeting search type
queryYesSearch query string
locationIdNoLocation identifier
searchTypeNoSpecific search subtype

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.1.0
    • addedInput schema / properties / type / enum
      Added value: +[
      +  "geolocation",
      +  "interest",
      +  "language"
      +]
  2. First observedv2.0.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds genuine context beyond annotations: type-dependent response shapes, that geolocation/interest payloads are raw pass-throughs in snake_case, and the required adPublishing.readonly scope. Pagination/result limits are not mentioned.

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 type-to-response-shape mapping is front-loaded and high value, and endpoint/scope metadata is compact. Minor waste in the redundant first line that only restates the title.

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

Completeness4/5

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

With no output schema, the description compensates by describing what each type returns and the field casing, which is what an agent needs to consume results. Gaps remain around result limits, pagination, and the relationship between `type` and the optional `searchType`.

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 baseline is 3; the description earns above baseline by mapping each `type` enum value to a distinct result taxonomy, information the schema's 'Targeting search type' does not convey. It says nothing about `locationId` or the overlapping `searchType` parameter, leaving their role ambiguous.

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 ('Search Facebook targeting options') plus the concrete downstream use case ('ad set audience building'). The platform qualifier separates it from the Google and LinkedIn targeting_search siblings without ambiguity.

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?

Explicitly explains what each `type` value selects and what it returns, which effectively tells the agent when to pick each mode. It does not, however, name the sibling tools (ghl_ad_google_targeting_search / ghl_ad_li_targeting_search) or state exclusions.

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