Skip to main content
Glama

Honeyfield Marketing MCP

GA4: Manage audiences

ga4_manage_audiences
Destructive

GA4-Audiences (Remarketing, nach Google Ads exportierbar). action: list | create. property_id: die GA4-Property des Workspace (andere werden abgelehnt). create braucht 'definition' (Audience-Body nach API-Schema): displayName, description, membershipDurationDays (max. 540), filterClauses [{clauseType: INCLUDE|EXCLUDE, simpleFilter|sequenceFilter}], optional eventTrigger. validate_only gibt den Body zurück, ohne zu schreiben — und ohne Prüfung (die API kennt kein validate_only; 'validated' in der Antwort bedeutet keine Prüfung); Fehler zeigen sich erst beim echten create. workspace: Slug des Kunden-Workspace (optional bei nur einem Workspace).

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": {
      "action": "<action>",
      "property_id": "<property_id>"
    },
    "name": "ga4_manage_audiences"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
workspaceNo
definitionNo
property_idYes
validate_onlyNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the write risk is covered; the description goes beyond that with a genuinely non-obvious caveat: validate_only returns the body without writing and without any validation ('validated' in the response does not mean checked, errors surface only on the real create). It also notes the 540-day cap and cross-workspace rejection. It does not state permission requirements or whether the action set is limited to list|create with no update/delete path.

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 purpose and action values, then parameters, then the validate_only caveat, with almost no filler. The validate_only sentence is long and parenthetical-heavy, and the mixed German/English phrasing slightly slows parsing, but every clause adds information.

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?

An output schema exists, so return values need not be explained, and the definition body plus scoping rules are fully covered. The remaining gap is the mutation surface: with destructiveHint=true, it would help to state explicitly that this tool cannot update or delete audiences and what a failed create leaves behind. Broadly complete for a 5-param tool at 0% schema coverage.

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?

Schema description coverage is 0% and there are no enums, so the description carries the entire burden and does: it enumerates action values, explains property_id scoping, spells out the definition body fields (displayName, description, membershipDurationDays max 540, filterClauses with clauseType INCLUDE|EXCLUDE and simpleFilter|sequenceFilter, optional eventTrigger), defines validate_only, and explains the workspace slug fallback. No parameter is left undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific resource ("GA4-Audiences") and qualifies it as remarketing audiences exportable to Google Ads, and the first body line names the two operations (list | create). An agent immediately knows this reads and creates GA4 audience definitions, which no sibling does. It does not explicitly contrast with the ads_/meta_/linkedin_list_audiences siblings, but the GA4 scoping is sufficient to separate them.

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

Usage Guidelines3/5

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

Gives real preconditions: property_id must belong to the workspace (others are rejected), workspace is optional when only one exists, and create requires 'definition'. However, it never frames when to pick list versus create or when this tool is the right choice versus non-GA4 audience tools. Usage is implied by the action values rather than stated as guidance.

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