Ancient Echoes MCP

Tarot Preview

divination.preview_tarot

Read-only

Draws tarot cards for a selected deck and spread, returning card profiles, interpretations, reversal details, and random-source evidence without storing readings.

Instructions

按 tarot_deck_correspondence_profiles_v3_3 抽取指定牌系和牌阵，返回对应画像、解释画像、逆位请求/实效与随机来源证据，不保存记录。马赛不附加 Golden Dawn 对应；透特不生成逆位是产品牌系策略，不是普遍规则。带 seed 时先以 FNV-1a 64 位哈希再洗牌，且不保存 seed 明文。

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": {
      "question": "<question>"
    },
    "name": "divination.preview_tarot"
  }
}

Input Schema

Name	Required	Description
`deck`	No	rider_waite 使用 Golden Dawn 衍生对应；marseille 不附加该对应；thoth 使用克劳利/Golden Dawn 衍生对应
`seed`	No	可复现种子；服务以 FNV-1a 64 位哈希后交给 Go math/rand Perm，不保存明文
`notes`	No
`locale`	No
`spread`	No
`question`	Yes
`focus_area`	No
`allow_reversed`	No	请求逆位；Rider-Waite 与 Marseille 按请求执行，Thoth 保留请求值但本产品画像实际禁用

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.1Nov 9, 2026

TDQS

B3.2/5.0

Behavior4/5

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

The annotations only declare readOnlyHint=true, while the description adds meaningful behavior: no saved records, seed hashing with no plaintext storage, and deck-specific rules such as Marseille omitting Golden Dawn correspondences and Thoth disabling reversals as product policy. Return format and error conditions remain unspecified, but this is substantial context beyond the annotations.

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?

Three dense sentences front-load the purpose, then add deck-specific rules and seed handling. There is little filler, though the seed-hash detail duplicates the schema and the jargon reduces readability.

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?

The description covers core behavior and key deck/seed quirks for a read-only preview tool. However, with eight parameters, 38% schema coverage, and no output schema, it omits parameter meanings and return-structure details that an agent would need for precise invocation.

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

Parameters2/5

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

Schema description coverage is only 38%. The description mentions deck, spread, seed, and reversed cards, but largely restates the deck and seed schema text and leaves question, locale, focus_area, notes, and the spread enum meanings unexplained. It does not compensate enough for the low coverage.

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 action: draw cards from a named deck and spread, return profiles and interpretation, and explicitly save no records. The tarot purpose is clear, but it does not differentiate this tool from the many sibling divination.preview_* tools.

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?

There is no explicit when-to-use or when-not guidance. It implies a tarot reading for a question, but does not say when to choose it over other divination preview tools or what kinds of questions fit.

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

Deploy Server