Latest Korean headlines from Yonhap, Maeil Business and Hankyung, deduplicated and newest-first. Titles stay in Korean — use /api/news/headlines/en for English. Optional ?category=top|economy|tech|politics and ?limit=30 (max 100). Costs $0.01 in USDC per call, settled via x402.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max items (default 30, max 100) | |
| category | No | Filter by category |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
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 mentions deduplication, newest-first ordering, the Korean-only language constraint, and the $0.01 USDC cost settled via x402. It could additionally state that this is a read-only operation or describe error/rate-limit behavior, but the disclosed traits are meaningful and useful.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact: three sentences cover purpose, language caveat, alternative route, parameters, and cost. Information is front-loaded with the core purpose before auxiliary details. There is no fluff or redundant phrasing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple optional-parameter headline fetcher with no output schema, the description is nearly complete: it covers sources, ordering, deduplication, language, the sibling alternative, parameter constraints, and cost. It does not describe the response shape or pagination beyond limit, but that is a minor gap for this low-complexity tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already documents both parameters with 100% coverage, including the enum values and the max/default for limit. The description largely repeats this information rather than adding new semantic detail. It does restate the category options and default limit, which is harmless but not a significant value-add beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool as fetching the latest Korean headlines from three named sources. It also differentiates itself from the sibling tool by explicitly stating that titles stay in Korean and pointing to the English alternative. Deduplication and newest-first ordering add further precision.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit guidance on when to use this tool versus the English alternative: use this for Korean-only headlines, use the English endpoint when English titles are needed. It also states the optional category and limit parameters, giving an agent enough context to decide whether this is the right tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a fairly distinct resource and action: market snapshots vs. single tickers, current vs. historical vs. statistical kimchi premium, headlines vs. English headlines, and per-company vs. latest vs. consensus research. The main ambiguity is between preview_research and preview_research_coverage, and korea_market_snapshot overlaps with several individual data tools, but descriptions clarify the granularity and combined-briefing intent.
All tool names use a consistent lowercase snake_case convention with clear domain prefixes like crypto_krw_, kimchi_premium_, news_, preview_, and research_. The English variant news_headlines_en and the aggregate korea_market_snapshot still follow the same readable naming style.
Fifteen tools sit at the upper boundary of a well-scoped set, but each serves a clear purpose in a paid API that exposes market data, kimchi analytics, news, research, and free previews. The set is slightly broad because it spans two domains and includes aggregate and preview endpoints, but the count is defensible.
Core workflows are well covered: current and historical market data, USD/KRW, kimchi premium current/history/stats, translated news, per-company research, latest research, and consensus. Gaps are minor and mostly outside the stated scope, such as full-text news articles, historical crypto OHLC, or advanced research filtering by sector or brokerage.