Search and retrieve Ulsan University corporate and campus recruitment notices by page and keyword; use returned notice numbers to view full postings through job_detail.
본교 채용공지(기업 채용정보·교내채용): [번호] 구분 기업 제목 (등록일 ~ 마감일). keyword는 기업·제목에서 거른다 (앞 5쪽 안에서). 본문은 job_detail(번호).
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| limit | No | ||
| keyword | No |
| 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 exist, so the description carries the burden. It usefully discloses the result shape and the 5-page keyword scan limit, but says nothing about page/limit defaults, total result counts, or ordering beyond the field list. Meaningful but incomplete 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
Very compact, front-loaded with the resource and result shape, then the keyword rule and the detail-tool pointer. The bracketed field notation is dense but each fragment carries information.
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 need not be re-explained, yet the description still summarizes the fields and adds the paging caveat and sibling pointer. Complete enough for correct invocation; only pagination semantics remain thin.
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 compensate. It explains keyword semantics well (filters on company/title, scoped to first 5 pages), but page and limit are undocumented beyond their schema defaults. Partial compensation justifies a mid score.
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+resource: lists main-campus job postings, and enumerates the returned fields ([번호] 구분 기업 제목 (등록일 ~ 마감일)). It also names the sibling job_detail for body content, so an agent can distinguish list vs. detail without opening either schema.
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?
Explicitly routes to job_detail(번호) for postings' body, and discloses an important usage constraint: keyword only filters over the first 5 pages. Missing an explicit statement of when not to use it (e.g. vs. notices/site_search), but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.