Retrieve National Assembly speech video clips by meeting date, title, or member, showing question counts, speaking minutes, and per-member video segments with links for tracking legislative questions.
국회의원 발언영상 목록(회의 당일 저녁~다음 날 공개). 회의별로 누가 몇 번, 몇 분 질의했는지 준다. 발언 원문은 없다. member 를 주면 그 의원의 영상 구간(답변자·길이·영상 링크)까지 준다. 국감 회의 제목엔 위원회명이 없고 피감기관만 있다.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | 회의일 | |
| title | No | 회의 제목 일부, 예: 국정감사, 행정안전위원회 | |
| member | No | 의원 이름 |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does so well: it discloses publication latency (evening of the meeting day through the next day), states what is absent (no transcripts), and describes how the response expands when member is supplied (답변자·길이·영상 링크). It omits pagination, result caps, and any auth/rate context, keeping it from a 5.
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?
Five short sentences, each adding a distinct fact (timing, payload, exclusion, member behavior, title caveat), with the core purpose front-loaded. The telegraphic style is dense but nothing is wasted.
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 three-parameter, annotation-free tool with no output schema, the description covers what comes back, when the data exists, what it excludes, and a title-filter pitfall. Only the absence of pagination/result-size information leaves a small gap.
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 100%, so the baseline is 3, but the description adds genuine meaning beyond the schema: it explains that member switches the output to per-segment video data (answerer, length, link) and warns that audit meeting titles contain only the audited institution, not the committee name. That is real guidance the schema does not convey.
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 resource (국회의원 발언영상 목록) plus the shape of the payload (per-meeting counts and minutes per speaker), and explicitly excludes transcripts ("발언 원문은 없다"), which implicitly separates it from assembly_meeting_speeches. It never names a sibling tool outright, so it stops short of a 5.
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?
Usage is implied through the data-availability window (회의 당일 저녁~다음 날 공개) and the no-transcript caveat, and the note that audit meeting titles carry only the audited institution is a real operational hint for the title filter. However, it never says when to prefer assembly_meeting_speeches or assembly_live_captions instead, leaving the routing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.