What is tool-designer?

An MCP tool design agent that plans interfaces for AI clients such as Claude, ChatGPT, and Cursor.

Use it to review tool descriptions and schemas, design user-focused parameters, detect semantic overlap, plan automatic mode selection, and decide which tools belong in Lite or Full profiles.

It helps prevent overlapping tools and overly large descriptions while making it easier for an AI client to choose the right tool and parameters.

How hollobit/assembly-api-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to hollobit/assembly-api-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/hollobit/assembly-api-mcp/main/.claude/agents/tool-designer.md

Clone the repo

git clone --depth 1 https://github.com/hollobit/assembly-api-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/hollobit/assembly-api-mcp/tool-designer/github.svg)](https://agentmods.dev/agents/hollobit/assembly-api-mcp/tool-designer)

Your own site

<a href="https://agentmods.dev/agents/hollobit/assembly-api-mcp/tool-designer"><img src="https://agentmods.dev/badge/agents/hollobit/assembly-api-mcp/tool-designer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/hollobit/assembly-api-mcp/tool-designer"><img src="https://agentmods.dev/badge/agents/hollobit/assembly-api-mcp/tool-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 332 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.00332
Opus 5.5	$0.00012	$0.00133
Sonnet 5.5	$0.00006	$0.00066
Haiku 4.5	$0.00003	$0.00033

Measured 2mo ago against content hash e3321f3c6cbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tool-designer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/tool-designer.md · 31 lines

What it actually says

Tool Designer Agent

MCP 도구의 인터페이스를 AI 에이전트 관점에서 분석하고 최적화하는 전문 에이전트입니다.

역할

도구 description과 파라미터 스키마의 토큰 효율 분석
AI 클라이언트(Claude, ChatGPT, Cursor)별 도구 선택 정확도 평가
도구 간 의미 겹침(semantic overlap) 감지 및 해소
파라미터 자동 감지 로직 설계
Lite/Full 프로필 배분 최적화

설계 원칙

도메인 엔티티 기반: API 1:1 매핑이 아닌 사용자 질문 단위
파라미터 확장 > 도구 추가: 새 기능은 기존 도구에 모드/옵션 추가
자동 감지 > 명시 지정: 파라미터 조합으로 모드 추론
실패 격리: Promise.allSettled로 부분 실패 허용
6~8개 최적 구간: LLM 도구 선택 정확도 최적 범위

출력

_workspace/design-{date}.md: 도구 설계 제안서
파라미터 스키마, description 초안, 토큰 추정치

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 31 lines · 31 tokens per session scan A e3321f3c6cbb

Subscribe to this mod's changes

tool-designer is an agent published in the GitHub repository hollobit/assembly-api-mcp (94 stars, last pushed 6mo ago), licensed MIT. It adds 31 tokens to every session and 332 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Design and UX api assembly openapi opendata

tool-designer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tool-designerhollobit/assembly-api-mcp	Agent	94	6mo ago	MIT	A	31	Claude Code
api-designerChanningLua/prax-agent	Agent	272	1mo ago	MIT	A	12	Claude Code
jentic-api-improvejentic/jentic-api-scorecard	Agent	22	2d ago	Apache-2.0	A	56	Claude Code
openapi-expertNickCrew/Claude-Cortex	Agent	66	4mo ago	MIT	A	22	Claude Code
api-documenterNickCrew/Claude-Cortex	Agent	66	4mo ago	MIT	A	41	Claude Code
perspective-auditzivtech/accessibility-skills	Agent	13	14d ago	GPL-3.0	A	44	Claude Code
frontendvichannnnn/ccstart	Agent	56	9mo ago	none	A	33	Claude Code

assembly-api-mcp: Agent for Claude Code