Skip to main content
Glama

Check Google Consent Mode v2 setup (free)

consent_mode_check
Read-onlyIdempotent

Free, no sign-in: fetch a public page as a first-time visitor and check its Google Consent Mode v2 setup — whether gtag.js or Google Tag Manager is present, whether a consent default is set before the tags load, the default values of ad_storage, analytics_storage, ad_user_data and ad_personalization, whether wait_for_update, url_passthrough and ads_data_redaction are used, whether a consent banner is detected, and which tags fire before consent. Returns pass / warning / fail per check with plain-language fixes and copy-paste default snippets. It also reads the consent banner's own settings and, in country_rules, checks the banner rules that can be tested from outside for Italy (Garante 2021 guidelines) and Spain (AEPD cookie guide, July 2023 update), each with its source and a fix (automatic check, not legal advice). Static check (no JavaScript runs), so consent updates after a click aren't visible. Shares the free quota of 10 checks per hour per visitor with pre_consent_scan.

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": {
      "url": "<url>"
    },
    "name": "consent_mode_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesPublic page to check, e.g. https://example.com

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, and the description adds substantial context beyond them: no sign-in required, static (non-JS) execution with the consequence that post-click consent updates are invisible, and a concrete rate limit of 10 checks per hour per visitor shared with pre_consent_scan. It also discloses that country_rules is an automatic check and explicitly not legal advice, which is exactly the kind of caveat an agent needs.

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 free/no-sign-in qualifier is front-loaded, which is good, but the body is one very long run-on sentence stringing together a dozen check types, making it hard to scan. The content is largely load-bearing, yet the enumeration of every individual check exceeds what an invocation decision requires.

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, so the description must describe returns — and it does: pass/warning/fail per check, plain-language fixes, copy-paste default snippets, and per-country sources in country_rules. Combined with the explicit static-analysis limitation and quota, an agent has enough to call this correctly and set expectations for results.

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?

With a single parameter and 100% schema description coverage ('Public page to check, e.g. https://example.com'), the schema already carries the semantics. The description adds only marginal framing ('fetch a public page as a first-time visitor') and nothing about URL format constraints, redirects, or what makes a URL eligible beyond 'public'.

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 opens with a specific verb and resource ('fetch a public page... check its Google Consent Mode v2 setup') and enumerates exactly which signals are inspected (gtag/GTM presence, consent default ordering, ad_storage/analytics_storage defaults, wait_for_update, url_passthrough, ads_data_redaction, banner detection, tags firing before consent). However, it never positions itself against the closest siblings such as pre_consent_scan (mentioned only for quota sharing) or run_compliance_scan, so the agent must infer the split.

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 implied by the description ('check its Google Consent Mode v2 setup') and by the stated scope, but there is no explicit when-to-use/when-not guidance relative to pre_consent_scan or run_compliance_scan beyond a note that they share quota. The limitations ('static check, no JavaScript runs', Italy/Spain country_rules only) do help the agent judge suitability, which lifts it above no guidance at all.

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