Skip to main content
Glama

시퀀스 다이어그램 그리기

velog_render_sequence

Renders ordered participant messages into a sequence diagram PNG and uploads it to Velog. Auto-layouts call/return lifelines, notes, and alt/opt/loop fragments; validates geometry before publishing.

Instructions

참가자와 순서 있는 메시지로 시퀀스 다이어그램을 그려 PNG 로 만들고 벨로그에 올린다. 좌표를 받지 않는다 — 열 간격, 행 높이, 활성 막대, 묶음 상자를 전부 렌더러가 실측으로 정한다. 라벨이 안 들어가면 글자를 줄이는 게 아니라 그 구간을 넓히고, 길면 접고, 접힌 만큼 행을 높인다. 메시지는 배열 순서가 곧 시간 순서다. 중간에 하나를 끼워 넣어도 아래가 알아서 밀린다. 구성도나 흐름도(시간 축이 없는 그림)는 velog_render_diagram 을 쓸 것. 깔끔하게 나오는 건 레이아웃이 아니라 입력이 정한다. 세로 길이를 지배하는 셋:

  • call 에는 짝이 되는 return 을 붙인다. 안 닫힌 활성 막대는 계단처럼 겹쳐 쌓인다.

  • note 는 한 줄로 쓴다. 접힌 줄 수만큼 그 행이 통째로 높아진다.

  • 구분 기호(& ? = / , ; |)가 있는 긴 라벨은 렌더러가 그 뒤에서 끊는다. 그런 기호가 없는 긴 한글 토큰만 직접 끊어주면 된다. ⚠️ 자가감사 통과는 「보기 좋다」가 아니다. 감사는 기하만 본다 — 삐져나옴, 겹침, 관통, 상자 범위. 쌓인 막대도 어색한 줄바꿈도 통과시킨다. 감사에 걸리면 올리지 않고 무엇이 문제인지 알려준다. 이 판단은 끌 수 없고, 감사에 걸린 산출물은 velog_upload_image 로도 받지 않는다. 종류: call async return note 아이콘: alert arrow bell bolt branch browser cache chart check clock cloud code cross database file gear key layers lock mail mobile network package retry search server terminal user 톤: slate gray blue green amber yellow purple teal rose indigo

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
altNo이미지 대체 텍스트
titleYes그림 제목 (좌상단)
legendNo
uploadNo
numbersNo메시지 앞에 1. 2. 3. 을 붙인다
post_idNo붙일 글 id. 주면 벨로그가 내 글인지 확인한 뒤 받는다
messagesYes배열 순서가 시간 순서다. call 마다 짝이 되는 return 을 넣어야 활성 막대가 닫힌다
subtitleNo한 줄 설명·근거
fragmentsNoalt·opt·loop 묶음 상자. 서로 완전히 포개거나 완전히 떨어져야 한다
activationsNocall/return 짝에서 활성 막대를 뽑아 그린다
participantsYes왼쪽부터 순서대로 세로 열이 된다

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.0

TDQS

A4.9/5.0
Behavior5/5

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

The description discloses several behavioral traits beyond the minimal annotations: it uploads to Velog (side effect), it runs an automatic geometric audit that can reject output and prevent upload, the audit cannot be disabled, and rejected images cannot be uploaded via velog_upload_image. It also explains layout behaviors like auto-widening, folding, and how vertical size is dominated by input structure. These are valuable and non-obvious details that guide agent behavior.

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 description is long but well-structured: it leads with the core purpose, then a bold note about coordinates, then a warning about audit behavior, then a list of kinds, icons, and tones. Every sentence adds information, and formatting (bullets, bold) improves scannability. It is appropriately sized for the tool's complexity and avoids redundancy.

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?

For a tool with 11 parameters, no output schema, and rich behavioral rules, the description covers the essential context: when to use it, how to structure input for good results, what the audit does, and what happens on failure. It does not describe the return value explicitly, but given that the tool uploads and likely returns a reference, this is a minor gap. Overall, it is complete enough for an agent to call it correctly and anticipate outcomes.

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?

The schema already documents parameters well (82% coverage). The description adds some semantic context: message array order equals time order (also in schema), call needs matching return (also in schema), note is for description boxes (in schema). However, it adds new meaning about auto line-breaking on separators and the rule that only long Korean tokens without separators need manual breaking. This is helpful but not critical for parameter understanding since schema covers most, so a 4 is warranted.

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 clearly states the tool draws sequence diagrams from participants and ordered messages, renders them as PNG, and uploads to Velog. It explicitly distinguishes itself from velog_render_diagram by specifying that for non-temporal diagrams (구성도/흐름도), the sibling tool should be used. This leaves no ambiguity about what this tool does and how it differs.

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

Usage Guidelines5/5

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

The description provides explicit guidance on when to use this tool vs velog_render_diagram ('구성도나 흐름도(시간 축이 없는 그림)는 velog_render_diagram 을 쓸 것'). It also gives concrete input-shaping rules to achieve good output: matching calls with returns, keeping notes to one line, and handling long labels with separators. This is actionable usage instruction, not just a generic statement.

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