Skip to main content
Glama

Builderlog

홈판·검색 상위 글 공통점 점검

blog_homefeed_check
Read-only

초안의 제목 길이·답 단어·첫 문단 길이·이미지 수와 첫 이미지 자리·태그 수를, 홈판·검색 상위 글 199편을 직접 센 기준(종류별 4가지)과 견줘요. 경고만 돌려주고 노출·순위는 예측하지 않아요. 블로그 통계는 읽지 않고, 글을 고치거나 저장하지 않아요.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "body": "<body>"
    },
    "name": "blog_homefeed_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes초안 전체(마크다운, 첫 줄 “# 제목”, 이미지는 ![설명](주소) 줄로)
tagsNo붙일 태그들(선택, 개수만 견줘요)
titleNo제목(초안 첫 줄에 # 제목이 없을 때만)
profileNogeneral 일반 정보 · info 제품·IT 구매 · howto 사용법·설정 · entertainment 방송·연예(기본 general)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds genuinely new behavioral facts: output is warnings only, ranking/exposure is explicitly not predicted, blog statistics are not read, and nothing is edited or saved. The stated provenance of the baseline (199 posts, 4 criteria per category) also sets expectations about what the checks are grounded in. What it does not say is how many warnings or in what form they return, which keeps it below 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.

Conciseness4/5

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

Three sentences, front-loaded with the metric list, then the output nature, then the explicit non-actions — no filler. The metric enumeration is dense but each item maps to a real check; the phrasing '종류별 4가지' is slightly terse and could be misread, a minor cost in clarity for compactness.

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?

With no output schema, the description carries the burden of describing returns and does so at a high level (warnings only, no ranking prediction). It also discloses provenance of the baseline and the non-read of statistics, which an agent needs to set expectations. The main residual gap is the shape or count of warnings, which is not described beyond 'warnings only'.

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 every parameter including the profile enum is already documented in the schema; baseline is therefore 3. The description corroborates that tag count is compared and that the title/image checks operate on the body, but the profile parameter is never mentioned and no additional format or defaulting guidance is added.

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

Purpose4/5

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

States a concrete operation (compare the draft's title length, answer words, first-paragraph length, image count/position, tag count) against a fixed baseline of 199 top homefeed/search posts. This enumerates exactly which metrics are checked, which distinguishes it from single-metric siblings like blog_title_check or blog_tags even though no sibling is named. The verb is implicit in '견줘요' (compare) but the resource and scope are unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied by the term '초안' (draft) and by the statement that it returns warnings without predicting exposure or ranking, which tells the agent this is a pre-publish sanity check rather than an analytics tool. However, there is no explicit when-to-use/when-not guidance and no named alternative among blog_title_check, blog_depth_check, or blog_tags, so the agent must infer routing from the metric list alone.

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