Skip to main content
Glama
Sign In
shunshi-tarot-mcp

shunshi-tarot-mcp

Official
by shunshi-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

drawCards

Draws 1–10 unique tarot cards for supplied spread position labels without replacement, returning orientations and Waite reference meanings for AI interpretation.

Instructions

Draw unique cards without replacement using OS randomness. Supply 1–10 position labels BEFORE drawing, e.g. ['Past','Present','Future'] or ['Option A','Option B','Advice']. Reversals are independently 50% when enabled. Returns the cards, orientations and the matching Waite reference meanings; the calling AI interprets them. No prediction or LLM API calls.

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": {
      "positions": "<positions>"
    },
    "name": "drawCards"
  }
}

Input Schema

NameRequiredDescriptionDefault
localeNoen
positionsYes
allow_reversedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does so well: it discloses uniqueness (no replacement), the randomness source (OS), that reversals are independently 50% when enabled, what is returned, and that no LLM calls or predictions occur. It does not address failure modes, such as duplicate or excess position labels, which is the main remaining gap.

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?

Roughly five dense sentences, each carrying distinct information: mechanism, workflow constraint, probability behavior, return contents, and a scope disclaimer. Nothing is padded and the key constraint (labels before drawing) is front-loaded.

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

Completeness4/5

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

For a three-parameter stateless tool with no annotations and no output schema, the description covers the mechanism, the return contents (compensating for the missing output schema), and interpretation responsibility. The only substantive omission is the locale parameter's meaning and effect on returned reference meanings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does strong work on positions (1-10 labels, with example sets) and on allow_reversed (independent 50% reversal when enabled), but the locale parameter is not mentioned anywhere, leaving one of three parameters undocumented in both schema and description.

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 states a specific verb and resource (draw unique cards, without replacement, from OS randomness) and clarifies an important secondary behavior: it returns cards plus Waite reference meanings. It implicitly distinguishes itself from getCardMeaning by providing meanings inline, but never names the siblings listCards or getCardMeaning, so the differentiation is inferred 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 Guidelines3/5

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

It gives a workflow instruction that positions must be supplied BEFORE drawing, with concrete label examples such as ['Past','Present','Future'], and clarifies that the calling AI does the interpretation and no prediction happens. It does not say when to prefer this over listCards or getCardMeaning, so the usage guidance is implied rather than explicit.

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

Deploy Server

Other Tools