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

ghl-mcp-server-v2

by zackscriven

ghl_ad_google_target_interest_list

Read-onlyIdempotent

Retrieve affinity and in-market interest options for Google Ads targeting, with pagination and field projection to fetch only the needed audience data.

Instructions

Get target interests Retrieve affinity and in-market audience options for Google Ads targeting. Without limit the response is a plain array of root interests (each with a nested children tree). When limit is provided (max 100) the response is a paginated { targetInterests, paging } envelope — a page counts root interests; pass pageToken (from paging.next) to fetch the next batch. By default each node is returned in full; pass projection (comma-separated, e.g. ?projection=name,userInterestId,children) to return only the requested fields — selecting children prunes the whole tree recursively with the same selection, and any value outside the known field set is rejected. Endpoint: GET /ad-publishing/google/target-interests (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>",
      "type": "<type>",
      "advertisingChannelType": "<advertisingChannelType>"
    },
    "name": "ghl_ad_google_target_interest_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeYesInterest type
limitNoPage size for a paginated fetch (max 100). When set, the response is a { targetInterests, paging } envelope instead of a plain array. Counts root interests — each root includes its full children tree.
pageTokenNoOpaque cursor for the next batch, taken from the previous response paging.next
locationIdYesLocation identifier
projectionNoFields to return on each interest node, comma-separated (e.g. ?projection=name,userInterestId,children). When set, only the requested fields are returned. Selecting `children` prunes the whole tree recursively with the same selection; `availabilities` returns the whole array. Any value outside the known field set is rejected. Omit the param entirely to receive the full node as-is.
advertisingChannelTypeYesChannel type

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv2.1.0
    • addedInput schema / properties / limit
      Added value: +{
      +  "description": "Page size for a paginated fetch (max 100). When set, the response is a { targetInterests, paging } envelope instead of a plain array. Counts root interests — each root includes its full children tree.",
      +  "example": "100",
      +  "type": "string"
      +}
    • addedInput schema / properties / pageToken
      Added value: +{
      +  "description": "Opaque cursor for the next batch, taken from the previous response paging.next",
      +  "example": "100",
      +  "type": "string"
      +}
    • addedInput schema / properties / projection
      Added value: +{
      +  "description": "Fields to return on each interest node, comma-separated (e.g. ?projection=name,userInterestId,children). When set, only the requested fields are returned. Selecting `children` prunes the whole tree recursively with the same selection; `availabilities` returns the whole array. Any value outside the known field set is rejected. Omit the param entirely to receive the full node as-is.",
      +  "example": [
      +    "name",
      +    "userInterestId",
      +    "children"
      +  ],
      +  "items": {
      +    "enum": [
      +      "resourceName",
      +      "taxonomyType",
      +      "userInterestId",
      +      "name",
      +      "userInterestParent",
      +      "availabilities",
      +      "children"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  2. First observedv2.0.0

TDQS

A4/5.0
Behavior5/5

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

The description discloses unusual behavior that the annotations cannot: the response shape changes from a plain array to a { targetInterests, paging } envelope depending on whether limit is set, and unknown projection values are rejected. It also explains the recursive pruning semantics of selecting children, which is exactly the kind of non-obvious trait an agent needs 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?

It is front-loaded with purpose and then the response-shape rules, and most sentences carry real information. The trailing metadata block (source path v3/ad-publishing-v3.json) and the odd 'Pagination params: limit — pass them to page through full result sets' tail are redundant against earlier sentences.

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, and the description compensates fully by specifying both possible return shapes, how paging works, and how projection reshapes the tree. An agent has everything needed to call this correctly and parse the result.

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

Parameters3/5

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

Schema coverage is 100% and the schema descriptions already spell out limit, pageToken, and projection semantics in nearly the same words, so the description adds little beyond the structured fields. It correctly explains that limit counts root interests and that pageToken comes from paging.next, but this is restated rather than new, which puts it at the baseline 3.

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?

The description names a specific verb and resource: retrieve affinity and in-market audience options for Google Ads targeting, and the endpoint reinforces this. It is clear what is returned and why, but it never differentiates itself from nearby siblings such as ghl_ad_google_targeting_search or ghl_ad_google_audience_list, so an agent must infer which of these to pick.

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?

Usage is only implied through context ('for Google Ads targeting') and through the conditional limit/projection behavior. There is no explicit statement of when to reach for this tool versus ghl_ad_google_targeting_search, and no prerequisites (for example, that a Google Ads integration and locationId are required) are stated.

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