Skip to main content
Glama
korea-data-mcp

korea-data-mcp

by parkseokjune

hwahae_reviews

Fetch Hwahae K-beauty product reviews and ratings as clean English JSON, with optional ingredient breakdowns, to support product research and comparison.

Instructions

Return Hwahae (Korea's largest cosmetics review app) K-beauty product reviews and ratings as clean English JSON, optionally including ingredient breakdowns.

Args: maxProducts: Maximum number of products to return. includeIngredients: Whether to include ingredient data for each product. maxReviewsPerProduct: Maximum reviews to fetch per product.

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": "hwahae_reviews"
  }
}

Input Schema

NameRequiredDescriptionDefault
maxProductsNo
includeIngredientsNo
maxReviewsPerProductNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations, the description carries the full behavioral burden and leaves major gaps: it doesn't say whether data is scraped live, whether requests are rate-limited, how long ingredient fetching takes, or what happens when a product has no reviews. 'Clean English JSON' implies translation/normalization, which is useful, but that is the only behavioral disclosure.

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-loaded purpose sentence followed by a compact args list; no filler or marketing padding. The formatting is easy to scan, though the args block adds little beyond the parameter names.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values needn't be explained, and the parameter list is enumerated. Still, for a three-parameter scraping-style tool with zero annotation coverage and no documented defaults, limits, or failure behavior, the definition stops short of what an agent needs to call it confidently.

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 description coverage is 0%, so the description must compensate, and it does partially by giving a one-line gloss for each of the three parameters. However, the glosses largely restate the names, and the schema defaults (40 products, 20 reviews, ingredients off) plus any cost implications of large values are never mentioned.

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?

States a specific verb and resource ('Return Hwahae ... K-beauty product reviews and ratings') and adds identity context ('Korea's largest cosmetics review app') plus the output shape ('clean English JSON'). It is clear what the tool does, though it never contrasts itself with siblings like glowpick_rankings or oliveyoung_rankings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this versus the ranking-style siblings in the same Korean-commerce family, and no prerequisites or exclusions are stated. The only usage signal is 'optionally including ingredient breakdowns', which describes a parameter, not a use case.

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