Skip to main content
Glama

generate_hint_programmers

Generate step-by-step hints for Programmers coding problems. Adapts hint levels to user progress: analysis, core idea, or solution.

Instructions

프로그래머스 문제 힌트 생성. 3단계 가이드 프롬프트 제공.

🎯 핵심: 한 번에 1개 레벨 힌트만 제공. 1,2,3 단계를 동시에 제시하지 마세요.

📋 응답에 포함된 정보:

  • hint_levels[0]: Level 1 - 문제 분석 (처음 시도)

  • hint_levels[1]: Level 2 - 핵심 아이디어 (부분 구현)

  • hint_levels[2]: Level 3 - 상세 풀이 (거의 완성)

🤖 사용자 상황 판단 → 적절한 1개 레벨만 제시:

1️⃣ Level 1 제시 (처음/막힐 때): "사용자가 코드 없거나 어디서부터 시작해야 할지 모를 때" → hint_levels[0].prompt로 문제 접근법 제시

2️⃣ Level 2 제시 (다시 요청하거나 부분 구현 언급): "사용자가 '더 필요해', '더 자세히' 요청하거나, 이미 코드를 시작했다고 언급" → hint_levels[1].prompt로 핵심 로직 제시

3️⃣ Level 3 제시 (상세 풀이 명시 요청): "사용자가 '정답', '풀이', '코드' 등 최종 답변 요청" → hint_levels[2].prompt로 상세 구현 가이드 제시

📖 [권장] 어려운 문제는 본문 먼저 확인:

  • 난이도 높은 문제(Lv. 3 이상)는 메타데이터만으로 부족할 수 있음

  • fetch_problem_content_programmers로 실제 문제 본문 확인 후 힌트 생성 권장

정답 정책: 힌트만 기본 제공. 사용자가 "정답", "풀이", "코드" 명시 요청 시만 전체 풀이 제공.

⚠️ 플랫폼 판별: 문제 번호만 입력된 경우 대화 맥락에서 플랫폼을 파악하거나, 맥락이 없으면 반드시 BOJ/프로그래머스 중 어느 플랫폼인지 사용자에게 확인 후 호출하세요.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
problem_idYes프로그래머스 문제 ID 또는 URL
Behavior5/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It explains the response structure (hint_levels array with prompts), enforces a strict 'one level at a time' policy, and states the answer policy ('정답 정책') that full solutions are only provided on explicit request. This goes well beyond typical descriptions.

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?

Though lengthy, the description is exceptionally well-structured with emojis, numbered lists, and clear sections. Every sentence provides operational guidance, and the key rule—'provide only one hint level at a time'—is front-loaded. There is no filler or 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?

Given the lack of output schema and annotations, the description fully specifies the response format (hint_levels[0..2].prompt), the situation-based selection algorithm, the answer policy, and integration with fetch_problem_content_programmers. It leaves no critical behavioral or usage aspect unexplained.

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 input schema already covers the single problem_id parameter at 100%, so the baseline is 3. The description adds meaningful extra context by warning that a bare problem number may be ambiguous between BOJ and Programmers, and instructs asking the user for platform if context is missing. It also advises fetching problem content for high-difficulty problems, enriching the parameter's usage semantics.

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 '프로그래머스 문제 힌트 생성' (Programmers problem hint generation) and '3단계 가이드 프롬프트 제공' (provides a 3-step guide prompt). It specifies both the action (generating hints) and the resource (Programmers problems), distinguishing it from the sibling generate_hint_boj tool.

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 a detailed decision tree for when to present each of the three hint levels (Level 1 when stuck, Level 2 on re-request/partial implementation, Level 3 on explicit solution request). It also recommends using fetch_problem_content_programmers for difficult problems and includes platform disambiguation rules when only a bare number is provided.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/itsme-shawn/algoKit-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server