Search Ulsan University homepage content and board posts for keywords missing from menus, with optional filters for pages or posts.
울산대 홈페이지 통합검색: 메뉴 이름에 없는 단어도 페이지 본문·게시판 글에서 찾는다(예: '근로장학', '교환학생', '전과'). kind: ''(전체) / 'C'(안내 페이지만) / 'B'(게시판 글만, 더 많이). 결과의 mCode는 site_page로, board_seq는 notice_detail로.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | ||
| keyword | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, so the description carries the full burden, and it does disclose nontrivial behavior: the search reaches page body and board text, and kind='B' returns 'more' results than info-page-only search. It doesn't mention result limits, pagination, or auth, but the core behavioral shape is clear.
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?
Three short sentences, front-loaded with the search scope, then the kind options, then the result routing. No filler; the parenthetical examples earn their place by disambiguating the tool's reach.
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?
An output schema exists so return values needn't be explained, and the description complements it by naming the fields that matter for follow-up calls (mCode, board_seq). Minor gap: no mention of result volume caps or ordering, which matters for a search tool returning 'more' items.
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?
Schema coverage is 0%, so the description must supply the missing semantics — and it fully defines kind's three values ('', 'C', 'B') with their meaning and the volume tradeoff, which the bare schema does not convey at all. keyword's meaning is evident from the search 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?
States a specific verb and resource (통합검색 over page bodies and board posts) and explicitly differentiates itself from menu-name lookup by noting it finds words not in menu names. The examples ('근로장학', '교환학생', '전과') make the retrieval scope concrete and distinguishable from site_menu/site_page.
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?
Gives a clear use condition (searching terms absent from menu names) and tells the agent where to take results via the mCode → site_page and board_seq → notice_detail routing. It stops short of an explicit 'use site_menu instead for menu names' exclusion, but the alternative path is strongly implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.