Skip to main content
Glama

Builderlog

내 말투 규칙표 만들기

blog_voice_profile
Read-only

내가 직접 쓴 글 2~3단락 이상에서 문장 길이·어미·끝맺음·말버릇·부호·경험을 말하는 방식을 세어 글을 쓰는 AI 에게 줄 말투 규칙표로 돌려줘요. 글을 새로 쓰거나 고치지 않고, 이메일·전화 모양은 가려서 보여 주며, 저장하지 않아요. 글이 짧으면 규칙을 만들지 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_voice_profile"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes내가 직접 쓴 글(문장 10개·300자 이상, 최대 12,000자)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond readOnlyHint=true and openWorldHint=false, it discloses that no new text is written or edited, that email/phone patterns are masked in the output, and that nothing is persisted. Those are exactly the privacy and side-effect facts an agent cannot get from the annotations, and the short-input failure mode is stated too.

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 in the first clause, and the remaining clauses each carry a distinct fact (non-editing, masking, non-persistence, length floor) with no filler. It is one dense sentence, slightly run-on, but nothing is redundant.

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

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must characterize the return value — and it does, listing the exact dimensions counted and framing the result as a rule sheet for an AI writer. Combined with the privacy, persistence, and length constraints, an agent has everything needed to decide and call correctly.

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 100% and the single `body` parameter already documents the 10-sentence / 300–12,000 character bounds, so the baseline is 3. The description adds meaning on top by tying the input to '2~3단락 이상' and warning that short text yields no rules, which the schema alone does not convey.

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?

The description names a specific verb and artifact — it counts sentence length, endings, closings, verbal tics, punctuation and experience-expression from the user's own writing and returns a '말투 규칙표' for an AI writer. That is far more concrete than a restated title. It never explicitly contrasts itself with a sibling such as blog_ai_tone_check, so the differentiation is inferable rather than stated.

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?

It gives a clear entry condition (2~3단락 이상 of text you wrote yourself) and an explicit when-not (글이 짧으면 규칙을 만들지 않아요), which is actionable guidance. What is missing is any named alternative for adjacent tasks — e.g., when to run the tone-check sibling instead — so the 'alternatives' half of the guideline is absent.

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