Skip to main content
Glama

ENTERADS Free Shorts Library

영상 찾기 / Search videos

search_videos
Read-onlyIdempotent

무료로 받을 수 있는 완성 쇼츠 영상을 찾습니다(한 쪽에 12편, limit으로 1~50편). artist(아티스트 이름: 띄어쓰기나 대소문자가 달라도, 이름의 일부여도 한 팀으로 정해지면 그 팀), query(제목·아티스트 검색어), page(1부터)로 거를 수 있습니다. 받기 링크와 설명은 get_video로 받으세요. Searches the free, finished YouTube Shorts (12 per page; limit sets 1 to 50) by artist name (spacing and letter case are ignored, and part of a name is enough when it points to one artist), a title/artist keyword and page; call get_video for the download link, title and description.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_videos"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo쪽 번호(기본 1) / page number, default 1
limitNo한 쪽에 받을 편수(1~50, 기본 12) / videos per page, 1 to 50, default 12
queryNo제목·아티스트에 들어 있는 말 / keyword contained in the title or artist
artistNo아티스트 이름(list_artists의 이름. 조금 달라도 한 팀으로 정해지면 그 팀으로 찾음) / artist name from list_artists (a close or partial name is used when it points to one artist)

Output Schema

NameRequiredDescriptionDefault
pageYes
itemsYes
pagesYes
queryNo검색어 / keyword
totalYes
artistNo거른 아티스트(라이브러리의 이름) / artist filter (the name in the library)
noticeNoartist를 검색어로 바꿔 찾았을 때의 안내 / set when the artist given was searched as a keyword instead
next_pageYes다음 쪽 / next page
page_sizeYes
browse_urlYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / artist / description
      Previous value: -"아티스트 이름(정확히 같은 이름) / exact artist name from list_artists"New value: +"아티스트 이름(list_artists의 이름. 조금 달라도 한 팀으로 정해지면 그 팀으로 찾음) / artist name from list_artists (a close or partial name is used when it points to one artist)"
    • addedInput schema / properties / limit
      Added value: +{
      +  "description": "한 쪽에 받을 편수(1~50, 기본 12) / videos per page, 1 to 50, default 12",
      +  "maximum": 50,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • changedInput schema / properties / page / description
      Previous value: -"쪽 번호(12편씩, 기본 1) / page number, 12 per page, default 1"New value: +"쪽 번호(기본 1) / page number, default 1"
    • changedOutput schema / properties / artist / description
      Previous value: -"거른 아티스트 / artist filter"New value: +"거른 아티스트(라이브러리의 이름) / artist filter (the name in the library)"
    • addedOutput schema / properties / notice
      Added value: +{
      +  "description": "artist를 검색어로 바꿔 찾았을 때의 안내 / set when the artist given was searched as a keyword instead",
      +  "type": "string"
      +}
  2. First observed

TDQS

A3.9/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, safe, idempotent, closed-world behaviour, so the safety profile is covered. The description adds genuine matching semantics beyond that – spacing and letter case are ignored and partial artist names resolve to a team – but says nothing about result ordering, empty results, or how filters interact, which matters for a search tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded and each sentence carries information (page size, limit bounds, fuzzy artist matching, get_video handoff). The full Korean/English duplication roughly doubles length without adding new information, which is the only structural weakness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

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 described, and annotations cover safety. The one real gap is the combination semantics of artist plus query and what ordering/paging beyond page 1 yields, which an agent cannot infer from the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four params are already documented, including the list_artists reference and the 1-50 limit range. The description largely restates that (limits, page starts at 1, fuzzy artist matching) rather than adding syntax or precedence rules, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: searching free, finished YouTube Shorts, with the three filter dimensions (artist, query, page) named. It explicitly routes the agent elsewhere for download links (get_video), so it is distinguishable from its sibling 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.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context: use this to find finished Shorts, then call get_video for the download link, title and description. There is no explicit when-not or exclusion, and it does not state whether artist and query combine as AND or OR, but the handoff to the sibling is explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources