Skip to main content
Glama

Builderlog

블로그 초안 점검

blog_check
Read-only

네이버 블로그 초안을 기계 규칙으로 점검해요(제목 길이·키워드 위치·과장어·본문 길이·소제목 수·금지어·붙여 넣으면 깨지는 줄 등). 초안 형식은 첫 줄 "# 제목", 소제목은 "> " 로 시작하는 한 줄. 고칠 것과 권함 목록만 돌려주고 글을 고치거나 올리지 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_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes초안 전체(마크다운)
kindNo글 종류: general 일반 정보 · howto 사용법·설정 · money 돈·세금·계산 · it IT·제품 가격 · entertainment 방송·연예 리뷰 · review 제품 후기(직접 써 본 것) · visit 방문 후기(맛집·장소, 직접 가 본 곳)
titleNo제목(초안 첫 줄 # 제목이면 비워도 됨)
keywordNo
past_titlesNo이미 올린 내 글 제목들(겹침 확인, 선택)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover safety (readOnlyHint, openWorldHint=false, and it does not contradict them). The description still adds real behavioral content: the exact draft format expected (first line "# 제목", subheadings as "> " one-liners) and a precise statement of what the call yields — a fix list plus recommendations and nothing else. It adds the shape of the response without repeating the annotation.

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 purpose, then the format contract, then the output/scope guarantee. The parenthetical rule list is long but each item tells the agent what will be flagged. Little waste, though the enumeration could be tightened.

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?

For a read-only lint tool with no output schema, the definition covers what is checked, what input format is required, and what kind of result comes back. It would be fully complete if it hinted at how findings are prioritized or whether checks vary by the `kind` parameter.

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

Parameters4/5

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

Schema coverage is 80%, so the baseline is 3, but the description goes beyond the schema's bare "초안 전체(마크다운)" by specifying the structural contract the body must satisfy (title line and subheadings). That is meaningful added meaning for the most important parameter and explains why the separate `title` parameter may be left empty.

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 specific verb and resource (네이버 블로그 초안을 기계 규칙으로 점검) and enumerates the concrete rule categories: title length, keyword position, exaggeration words, body length, subheading count, banned words, paste-breaking lines. An agent immediately knows what this does. It does not differentiate itself from siblings such as blog_title_check or blog_ai_tone_check, which overlap in scope, keeping it at 4.

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 only implied — check a draft before publishing — with no explicit statement of when to choose this over blog_title_check, blog_depth_check, or blog_ai_tone_check. The closing clause does usefully bound scope (returns only fix lists, does not edit or post), but that is a scope statement rather than routing guidance.

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