Skip to main content
Glama
takada-at

Fortune MCP Server

by takada-at

draw_tarot

Perform tarot readings with customizable card counts. Receive detailed divination results for insights or guidance using the Fortune MCP Server's tarot tool.

Instructions

タロットカードを引いて占い結果を返します

Args:
    count: 引くカードの枚数(1-10、デフォルト: 3)

Returns:
    タロット占いの結果

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The draw_tarot tool handler, decorated with @mcp.tool() for registration in FastMCP. Draws a specified number (default 3, clamped 1-10) of random tarot cards from major and minor arcana lists, retrieves their meanings from the card_meanings dictionary, and formats a result string.
    @mcp.tool()
    def draw_tarot(count: int = 3) -> str:
        """タロットカードを引いて占い結果を返します
        
        Args:
            count: 引くカードの枚数(1-10、デフォルト: 3)
        
        Returns:
            タロット占いの結果
        """
        # カード枚数の制限
        count = max(1, min(count, 10))
        
        all_cards = major_arcana + minor_arcana
        drawn_cards = random.sample(all_cards, min(count, len(all_cards)))
        
        result_text = "🔮 タロットカードの結果 🔮\n\n"
        for i, card in enumerate(drawn_cards, 1):
            meaning = card_meanings.get(card, "意味不明")
            result_text += f"{i}. {card}\n   → {meaning}\n\n"
        
        return result_text
  • List of 22 Major Arcana tarot cards used by the draw_tarot tool.
    major_arcana = [
        "愚者", "魔術師", "女教皇", "皇帝", "皇后", "恋人", "戦車", "力", "隠者", 
        "運命の輪", "正義", "吊るされた男", "死神", "節制", "悪魔", "塔", 
        "星", "月", "太陽", "審判", "世界"
    ]
  • List of 56 Minor Arcana tarot cards used by the draw_tarot tool.
    minor_arcana = [
        "ワンドのエース", "ワンドの2", "ワンドの3", "ワンドの4", "ワンドの5", 
        "ワンドの6", "ワンドの7", "ワンドの8", "ワンドの9", "ワンドの10", 
        "カップのエース", "カップの2", "カップの3", "カップの4", "カップの5", 
        "カップの6", "カップの7", "カップの8", "カップの9", "カップの10", 
        "ソードのエース", "ソードの2", "ソードの3", "ソードの4", "ソードの5", 
        "ソードの6", "ソードの7", "ソードの8", "ソードの9", "ソードの10", 
        "ペンタクルスのエース", "ペンタクルスの2", "ペンタクルスの3", "ペンタクルスの4", 
        "ペンタクルスの5", "ペンタクルスの6", "ペンタクルスの7", "ペンタクルスの8", 
        "ペンタクルスの9", "ペンタクルスの10"
  • Dictionary mapping each tarot card to its meaning in Japanese, used by draw_tarot to provide interpretations.
    card_meanings = {
        "愚者": "新しい始まり、自由、無限の可能性",
        "魔術師": "スキル、集中、行動を起こす時",
        "女教皇": "直感、神秘、内なる知恵",
        "皇帝": "権力、支配、安定",
        "皇后": "育成、愛、創造性",
        "恋人": "愛、選択、バランス",
        "戦車": "勝利、意志の力、成功",
        "力": "勇気、忍耐、自己制御",
        "隠者": "自己探求、孤独、内なる知恵",
        "運命の輪": "運命の流れ、変化の時",
        "正義": "公正、バランス、法律",
        "吊るされた男": "視点の変更、犠牲、沈黙",
        "死神": "終わり、再生、変革",
        "節制": "調和、バランス、自己制御",
        "悪魔": "誘惑、束縛、依存",
        "塔": "破壊、予期せぬ変化、覚醒",
        "星": "希望、癒し、インスピレーション",
        "月": "幻影、不安、隠されたもの",
        "太陽": "成功、活力、喜び",
        "審判": "再生、覚醒、評価",
        "世界": "完成、調和、達成",
        "ワンドのエース": "創造の始まり、新しいアイデアの誕生",
        "ワンドの2": "計画、展望、期待",
        "ワンドの3": "協力、成長、成果",
        "ワンドの4": "安定、家庭、祝い",
        "ワンドの5": "競争、対立、挑戦",
        "ワンドの6": "勝利、名声、成果",
        "ワンドの7": "防御、挑戦に立ち向かう",
        "ワンドの8": "急速な進展、動き",
        "ワンドの9": "持ちこたえる、最後の努力",
        "ワンドの10": "重荷、責任、過度な負担",
        "カップのエース": "感情の始まり、愛の新しい局面",
        "カップの2": "感情の共有、パートナーシップ",
        "カップの3": "友情、祝い、楽しみ",
        "カップの4": "退屈、不満、感情の停滞",
        "カップの5": "失望、後悔、過去に囚われる",
        "カップの6": "懐かしさ、過去の思い出",
        "カップの7": "幻想、選択、迷い",
        "カップの8": "感情の断絶、離れる決断",
        "カップの9": "願望成就、幸福感",
        "カップの10": "感情の充実、家族や愛情の充足",
        "ソードのエース": "精神的な力、真実の探求",
        "ソードの2": "選択の困難、決断を下す時",
        "ソードの3": "心の痛み、別れ、失恋",
        "ソードの4": "休息、癒し、回復",
        "ソードの5": "敗北、騙し合い、苦しみ",
        "ソードの6": "移動、過去からの脱却、新しい環境への移行",
        "ソードの7": "策略、秘密、予期しない事態",
        "ソードの8": "束縛、抑圧、自己制限",
        "ソードの9": "不安、夜の恐怖、心配事",
        "ソードの10": "終わり、絶望、痛み",
        "ペンタクルスのエース": "物質的な繁栄、新たなチャンス",
        "ペンタクルスの2": "バランス、柔軟性、調整",
        "ペンタクルスの3": "協力、チームワーク、スキルの向上",
        "ペンタクルスの4": "保守、貯金、安定",
        "ペンタクルスの5": "貧困、困難、犠牲",
        "ペンタクルスの6": "施し、与えること、調和",
        "ペンタクルスの7": "長期的な視野、投資、結果を待つ",
        "ペンタクルスの8": "努力、勤勉、仕事に集中",
        "ペンタクルスの9": "物質的な成功、安定、満足",
        "ペンタクルスの10": "繁栄、家族、永続的な成功",
    }
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool draws tarot cards and returns results, implying a read-only operation, but does not address potential behavioral traits such as randomness, rate limits, authentication needs, or side effects. This leaves significant gaps in understanding how the tool behaves beyond its basic function.

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?

The description is appropriately sized and front-loaded, with the core purpose stated first, followed by parameter and return details. It uses clear sections ('Args:', 'Returns:') for structure, though the return statement is vague. There is minimal waste, making it efficient for an agent to parse.

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

Completeness3/5

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

Given the tool's low complexity (one parameter) and the presence of an output schema, the description is somewhat complete but has gaps. It explains the parameter well and states the return purpose, but lacks behavioral context and usage guidelines. The output schema should cover return values, so the description's vagueness on returns is acceptable, but overall it could be more comprehensive for a tool with no annotations.

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 description adds meaningful semantics for the single parameter 'count', explaining it as '引くカードの枚数(1-10、デフォルト: 3)' (number of cards to draw, 1-10, default: 3). This provides context beyond the input schema, which only defines the parameter type and default without describing its purpose or constraints. Since schema description coverage is 0%, the description compensates well for the single parameter.

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 clearly states the tool's purpose: 'タロットカードを引いて占い結果を返します' (Draw tarot cards and return fortune-telling results). It specifies the verb ('draw') and resource ('tarot cards'), though it doesn't explicitly differentiate from the sibling tool 'get_horoscope', which suggests a different fortune-telling method. The purpose is clear but lacks sibling differentiation.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives like 'get_horoscope'. It mentions the tool's function but does not indicate specific contexts, prerequisites, or exclusions for its use, leaving the agent without explicit usage instructions.

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

Related 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/takada-at/fortune_mcp'

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