mcp

analyze_garm

Compute GARM brand safety score for a website or category.

Based on the GARM (Global Alliance for Responsible Media) Brand Suitability
Framework. Maps content categories to 11 GARM sensitive content categories
with risk levels (Floor, High, Medium, Low).

Can either:
1. Provide a URL - classification will be fetched and mapped to GARM
2. Provide category and sentiment directly for instant scoring

Score interpretation: higher = safer for advertising.
Floor categories (e.g., Adult) always score 0/F regardless of sentiment.

Args:
    category: LLMSE category (e.g., "Adult", "Politics", "Sports").
    sentiment: Content sentiment ("Bad", "Neutral", "Good").
    url: Optional URL to analyze (fetches classification from cache).

Returns:
    GARM brand safety analysis with:
    - score: Brand safety score (0-100, higher = safer)
    - grade: Letter grade (A-F)
    - garm_category: Matched GARM category name or None
    - risk_level: "floor"|"high"|"medium"|"low"|"none"
    - is_floor: True if not suitable for any advertising
    - issues: Categorized issues {critical, warnings, info}
    - recommendations: Improvement suggestions

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	No
`category`	No
`sentiment`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It thoroughly explains the GARM scoring framework, the floor category behavior (always 0 regardless of sentiment), the difference between URL-based cached classification and instant scoring, and the exact return structure. This is transparent and goes well beyond minimal expectations.

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?

The description is moderately long but well-structured with a summary, mode explanation, and separate Args/Returns sections. Each section earns its place, though there is slight redundancy between the risk-level list in the prose and the return field enumeration. It is front-loaded with the core purpose and remains readable.

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?

The description provides detailed return fields, risk levels, floor behavior, and the two usage modes, making it highly self-sufficient even with the output schema present. The only minor gap is not explicitly stating the mutual exclusivity of url vs category+sentiment (e.g., what happens if both are supplied), but the 'Can either' phrasing implies the intended contract.

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%, but the description compensates by explaining each parameter: category with concrete examples ('Adult', 'Politics', 'Sports'), sentiment with examples ('Bad', 'Neutral', 'Good'), and url as optional with caching behavior. The two-mode pattern also clarifies the intended parameter combinations, adding significant value beyond the raw schema.

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?

The description opens with 'Compute GARM brand safety score for a website or category,' clearly stating the specific action and resource. It distinguishes itself from sibling tools like analyze_seo and analyze_aeo by focusing on the GARM brand safety framework. The two execution modes (URL or category+sentiment) further clarify the scope.

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?

The description explicitly lists two usage modes: 'Provide a URL' or 'Provide category and sentiment directly,' giving clear scenarios for when to use the tool. However, it does not explicitly mention when not to use it or reference alternative tools, which would have made it a 5.

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

All mcp tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.6/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: analyze_aeo, analyze_eeat, analyze_garm, analyze_readability, analyze_seo, and analyze_wcag each target a specific evaluation dimension, while classify_url, find_similar_sites, and select_advertiser serve different auxiliary functions. The audit tool is explicitly positioned as a combined report, so there is no ambiguity about overlaps.

Naming Consistency4/5

Most tools follow a clear verb_noun pattern (analyze_aeo, classify_url, find_similar_sites, select_advertiser). The single exception is 'audit', which is a bare verb and breaks the established convention, making the set slightly inconsistent.

Tool Count5/5

With exactly 10 tools, the set is well-scoped for a website analysis and advertising platform. Each tool covers a distinct aspect of the domain without redundancy, and the count is comfortably within the ideal 3-15 range.

Completeness5/5

The tool surface covers the full lifecycle of website evaluation: classification, multiple analysis dimensions (SEO, EEAT, AEO, readability, WCAG, GARM), competitive analysis, and advertiser matching. The audit tool ties everything together, leaving no obvious gaps for the stated purpose.

Resources

Need Help?