Skip to main content
Glama

AdLoop

by com.getadloop
OverviewDiscussionsAdmin

Keyword ideas

discover_keywords
Read-only

Discover new keyword ideas using Google Ads Keyword Planner.

Mirrors the "Discover new keywords" UI in Keyword Planner: start with keywords (seed_keywords), start with a website (url), or both together for more targeted ideas. At least one of seed_keywords or url is required.

Returns keyword ideas sorted by avg monthly search volume, with competition level (LOW/MEDIUM/HIGH) and top-of-page bid range, plus the seeds used and insights.

Google Ads API: https://developers.google.com/google-ads/api/docs/start

Input Schema

NameRequiredDescriptionDefault
urlNoA landing page or site URL to extract ideas from, e.g. "https://example.com/products".
page_sizeNoMax keyword ideas to return (default 50, clamped to 1-1000).
customer_idNoGoogle Ads customer ID (digits, dashes allowed). Defaults to the configured account.
language_idNoLanguage constant ID (1000=English, 1001=German, 1002=French). Defaults to 1000.1000
geo_target_idNoGeo target constant ID (2276=Germany, 2840=USA, 2826=UK). Defaults to 2276.2276
seed_keywordsNoSeed terms, e.g. ["running shoes", "trail running"].
include_monthly_volumesNotrue adds per-month search history (last 24 months, top-20 ideas) plus a seasonality insight — relevant to questions about demand trends, seasonality, or "when should I ramp budget".

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedInput schema / properties / customer_id / description
      Added value: +"Google Ads customer ID (digits, dashes allowed). Defaults\nto the configured account."
    • addedInput schema / properties / geo_target_id / description
      Added value: +"Geo target constant ID (2276=Germany, 2840=USA, 2826=UK).\nDefaults to 2276."
    • addedInput schema / properties / include_monthly_volumes / description
      Added value: +"true adds per-month search history (last 24\nmonths, top-20 ideas) plus a seasonality insight — relevant to\nquestions about demand trends, seasonality, or \"when should I ramp\nbudget\"."
    • addedInput schema / properties / language_id / description
      Added value: +"Language constant ID (1000=English, 1001=German,\n1002=French). Defaults to 1000."
    • addedInput schema / properties / page_size / description
      Added value: +"Max keyword ideas to return (default 50, clamped to 1-1000)."
    • addedInput schema / properties / seed_keywords / description
      Added value: +"Seed terms, e.g. [\"running shoes\", \"trail running\"]."
    • addedInput schema / properties / url / description
      Added value: +"A landing page or site URL to extract ideas from, e.g.\n\"https://example.com/products\"."
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds the practical validation constraint ('at least one of seed_keywords or url is required') that the schema does not enforce (required=0), which is genuinely useful. Return-format details are somewhat redundant given the output schema, and it omits rate-limit/account requirements.

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?

Purpose is front-loaded, followed by entry modes, the requirement, and the return shape. Every sentence carries information, though the return-value sentence overlaps with the output schema and could be trimmed.

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?

For a 7-parameter tool with full schema coverage and an output schema, the description supplies the essential constraint and usage modes. It could still note account/auth expectations for customer_id and does not contrast with keyword-performance siblings, but nothing critical for correct invocation 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 description coverage is 100%, so the baseline is 3. The description adds combination semantics beyond the schema by explaining that seed_keywords and url can be combined 'for more targeted ideas' and that one is mandatory — meaning not conveyed by the raw property descriptions.

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 ('discover') and resource ('new keyword ideas') via Google Ads Keyword Planner, and clearly disambiguates its scope from sibling research tools like get_keyword_performance (existing keywords) and draft_keywords (writing). The three seed/url entry modes make the tool's role unambiguous.

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?

Explains the three input modes (seed keywords, website url, or both) and the gating condition that at least one of seed_keywords or url is required. It does not, however, explicitly contrast when to pick this over siblings such as get_search_terms or suggest_brands, so it falls short of a full when/when-not/alternatives statement.

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

All AdLoop toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources