Skip to main content
Glama

cookie_dark_patterns

Read-onlyIdempotent

[Deterministic banner UX analysis. Pure inspection, read-only, side-effect free]. Audits cookie banner markup and modals for illegal deceptive patterns under EDPB Guidelines 03/2022 and Garante Privacy rules: asymmetric button styling (nudging), missing first-layer reject button, pre-ticked checkboxes, and confirmshaming. Usage: Use this tool to detect manipulative consent UI design. For technical tracking script firing checks, use 'gdpr_cmp_tracker_audit' instead. Returns: JSON object with { hasRejectButtonFirstLayer: boolean, hasAsymmetricStyling: boolean, hasPreTickedCheckboxes: boolean, darkPatternViolationsCount: number, edpbComplianceStatus: 'COMPLIANT' | 'NON_COMPLIANT', identifiedPatterns: string[] }.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "cookie_dark_patterns"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoTarget website URL to fetch and audit (e.g. https://novapixel.it)
htmlContentNoRaw HTML content of page or CMP banner

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / url / description
      Previous value: -"Target website URL to fetch and audit"New value: +"Target website URL to fetch and audit (e.g. https://novapixel.it)"
  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 and idempotentHint, and the description reinforces them with 'Deterministic ... pure inspection, read-only, side-effect free' plus the legal basis (EDPB Guidelines 03/2022, Garante Privacy). It adds useful framing but leaves out operational behavior such as what happens when the URL fetch fails or whether the target page is retrieved live from the network.

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-loads identity in a bracketed tag, then purpose, then usage, then returns — a clean and scannable order. Slightly heavy with the double framing of read-only/side-effect free, but no sentence is genuinely wasted.

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?

With no output schema, the description correctly spells out the return object's fields and the enum values for edpbComplianceStatus, which is exactly what an agent needs. The only gap is the unresolved relationship between the two input parameters.

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%, so both parameters are already documented as url and htmlContent. The description adds nothing about how the two interact — notably whether htmlContent supersedes url — which is the one piece of meaning the schema does not supply. Baseline 3 applies.

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 and resource ('Audits cookie banner markup and modals') and enumerates the exact violations detected: asymmetric button styling, missing first-layer reject, pre-ticked checkboxes, confirmshaming. It also names the sibling it is not ('gdpr_cmp_tracker_audit'), so an agent can separate the two without opening either schema.

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?

Gives an explicit positive trigger ('detect manipulative consent UI design') and an explicit routing rule away from this tool for tracking-script checks. That is the when-to-use plus alternative pairing the dimension asks for.

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