Skip to main content
Glama

Honeyfield Marketing MCP

Meta Ads: Targeting search

meta_targeting_search
Read-only

Meta-Targeting-Schlüssel suchen (Metas Targeting Search) — DAS Werkzeug, bevor in meta_create_adset/meta_update_adset Städte, Regionen, PLZ, Interessen, Behaviors oder Sprachen gesetzt werden. Schlüssel nie raten. kind: 'city' (Städte; key + supports_region/country_code), 'region' (Bundesländer/Regionen), 'zip' (Postleitzahlen; key mit Landespräfix wie 'AT:5020', primary_city), 'country' (ISO-Code als key), 'geo' (country+region+city+zip in einer Suche; type je Treffer), 'interest' (Interessen: id, name, path, audience_size_lower/upper_bound, topic — q Pflicht, error=query_required), 'behavior' (Behaviors: id, name, path, description, Größe — Meta liefert die komplette Liste, q filtert sie hier über Name und Pfad), 'locale' (Sprachen: key als Ganzzahl, name — q darf leer sein = alle Sprachen bis limit). Andere Werte: error=invalid_kind. q: Suchbegriff, z.B. 'Salzburg', '5020', 'Wandern', 'German'. country_code: ISO-Code zum Eingrenzen der Geo-Suche (z.B. 'AT') — sonst findet 'Salzburg' auch Orte in anderen Ländern. limit: max. Treffer (Default 25; Metas eigener Default wären nur 8). Gibt es mehr Treffer als limit, kommt ein Objekt mit result und warning zurück — auch bei Behaviors/Sprachen, wo Meta keine Seiten meldet; dann limit erhöhen oder q präzisieren. Jeder Treffer trägt verwendung mit dem fertigen Parameter für meta_create_adset/meta_update_adset, z.B. "cities=[{'key': '2420605', 'radius_km': 17}]", "regions=['1234']", "zips=['AT:5020']", "countries=['AT']", "interest_ids=['6003...']", "behavior_ids=['...']", "locales=[5]". Dieselben Schlüssel gelten in excluded_geo_locations (z.B. {'zips': ['AT:5020']}). Leere Trefferliste = nichts gefunden (kein Fehler) — Schreibweise oder country_code prüfen. Nur Lesezugriff. workspace: Slug des Kunden-Workspace (optional bei nur einem Workspace).

Input Schema

NameRequiredDescriptionDefault
qNo
kindYes
limitNo
workspaceNo
country_codeNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

The description is highly transparent regarding its behavior, explaining that it is a 'Lesezugriff' (read-only access). Crucially, it details the structure of the 'verwendung' output parameter, showing exactly how the data will be formatted for subsequent tool calls.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is highly dense and technical, making it difficult to read efficiently. While the core purpose is front-loaded, the volume of complex, necessary technical details prevents it from scoring higher on structural efficiency.

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?

The description is a near-perfect single reference guide. It covers what the tool does, every input parameter (even `country_code` scoping), the output structure, and the operational limitations and expected outcomes for various data types.

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

Parameters5/5

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

Given that the schema description coverage is 0%, the description must be exhaustive. It successfully defines and explains the semantic meaning of every parameter—from 'kind' specifics (e.g., what a zip key needs) to 'q' examples ('Salzburg').

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?

The description starts immediately by clarifying its vital role: to find Meta targeting keys specifically required before using meta_create_adset or meta_update_adset. It functions as a necessary lookup tool, clearly distinguishing its purpose from other creative or campaign management siblings.

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?

It provides strict usage guidance, advising the AI to 'never guess keys' and detailing how to interpret the `limit` parameter if Meta returns more results than requested. It even explains the implication of an empty results list (it's not an error).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources