list_top_headlines'오늘 주요 뉴스', '지금 헤드라인', '메인 뉴스 뭐야', '제일 중요한 뉴스'처럼 편집부가 가장 비중 있게 배치한 머리기사를 물을 때 사용합니다. 조회수 인기 순위가 아니라 편집 비중 기준입니다 — '많이 본' 기사는 list_popular_news 를 쓰세요.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | 페이징 메타데이터(있을 때). | |
| items | No | 기사 카드 목록. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint. The description adds the key behavioral distinction that it selects based on editorial placement, not popularity, which goes beyond annotations.
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?
Two sentences: first gives usage examples, second clarifies the editorial basis and points to sibling. Every word earns its place, and key information is front-loaded.
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?
Given no parameters, annotations present, and an output schema (implied from context), the description fully equips an agent to understand when and how to invoke the tool, including differentiation from sibling tools.
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?
No parameters exist, so schema coverage is 100%. The description implicitly provides all needed context (no user input required). A score of 4 is appropriate as the description adds clarity about the tool's usage context.
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 states it returns top headlines based on editorial importance, with explicit example queries. It also distinguishes from list_popular_news, which returns most-read articles.
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 when-to-use examples ('오늘 주요 뉴스', '지금 헤드라인') and a when-not-to-use directive with a specific alternative tool (list_popular_news for '많이 본' 기사).
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 distinct purpose: horoscopes (daily vs MBTI), news listings (latest, most read, popular, recommended, timely, top headlines), sections, and search. Descriptions provide clear usage examples and explicitly differentiate similar-sounding tools like list_most_read_news (editor-curated) vs list_popular_news (view-count based).
All tool names follow a consistent verb_noun pattern in snake_case: get_ for horoscopes, list_ for various news lists and sections, and search_ for search. No mixing of camelCase or other conventions.
10 tools is appropriate for a news server. It covers the main news consumption patterns (latest, popular, recommended, by section, search) plus two specialized horoscope tools. Neither too sparse nor overwhelming.
The tool surface covers typical news site operations: browsing latest, popular (both view-based and editor-curated), by category, headlines, time-based recommendations, and search. Horoscope retrieval is an extra feature. The missing article text retrieval is intentional (metadata-only return). No obvious gaps for the intended domain.