Skip to main content
Glama

Builderlog

초안 깊이 점검(사실 반복·맺음·AI 검색 인용·숫자 대조)

blog_depth_check
Read-only

초안을 네 가지로 점검해요. 같은 금액·무게를 3번 넘게 말했는지, 맺음 질문이 하나인지, 소제목·첫 문단·출처 표기가 AI 검색에 인용되기 쉬운 모양인지, 그리고 source_text(근거 원문)를 주면 글의 숫자가 그 원문에 있는지. 사실 여부는 판단하지 않아요. 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_depth_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes초안 전체(마크다운)
source_textNo근거 원문(선택). 주면 글의 숫자가 이 원문에 있는지 대조해요

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description is fully consistent with them while adding meaningful semantics: it diagnoses but never edits or saves the draft, and it does not render factual judgments. The one missing behavioral detail is what the result actually looks like, since there is no output schema.

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

Conciseness5/5

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

The scope statement is front-loaded in the first clause, followed by a compact enumeration of the four checks, then two short exclusion sentences. Every sentence carries distinct information and nothing is padded.

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 simple two-parameter read-only diagnostic with no output schema, the description covers what is inspected, the optional source_text path, and the behavioral limits. The notable gap is the absence of any indication of the return shape (e.g., a per-check report), which would matter for a diagnostic tool.

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 the schema already explains both body and source_text. The description's mention that supplying source_text triggers a number-against-source comparison largely restates the schema's own wording, adding only mild conditional emphasis. Baseline 3 applies when the schema carries the parameter documentation.

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?

The description names a specific verb (점검) and resource (초안) and then enumerates the four exact checks it performs: repeated amount/weight mentions over three times, a single closing question, AI-search citation shape of subheading/first paragraph/source notation, and numeric cross-checking against source_text. This is far more precise than the sibling blog_dup_check or blog_ai_tone_check scope and lets an agent tell them apart.

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?

Usage conditions are clear: pass the full draft, and optionally supply source_text to trigger the numeric comparison. The description also explicitly excludes adjacent tasks (사실 여부는 판단하지 않아요, 글을 고치거나 저장하지 않아요), which steers the agent away from using it as a fact-checker or editor. It stops short of naming a specific alternative tool for those excluded tasks.

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