Skip to main content
Glama

Tarot card of the day

marselia_daily_card
Read-onlyIdempotent

Use this when a person asks for the tarot card of the day or today's card. It takes no question and does not draw a card for one person (marselia_draw_card does): the card is the same for everyone. Marselia's public card of the day, the one the page /daily shows: 1 upright Tarot de Marseille card for the current day in Paris, chosen by a published SHA-256 rule over the date, with its name in the language asked, the URL of its real plate image (a public domain BnF scan, to be shown whole in its 440:827 frame), its keywords, the card of the day text of its card page, the card page, the page of the day, and the rule with the day's seed and index. Today only, upright, a theme for the day. Nothing is stored. Cite Marselia and the returned page URL.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "marselia_daily_card"
  }
}

Input Schema

NameRequiredDescriptionDefault
localeNoLanguage of the answer: en, fr, es, it, ar, tr, de, pt, nl, zh, ja, ko, pl, el, zh-TW. Default en. A regional tag such as fr-FR is read as its language.en

Output Schema

NameRequiredDescriptionDefault
urlYes
cardYes
dateYes
drawYes
textYes
localeYes
displayYes
drawUrlYes
keywordsYes
timeZoneYes
dateLabelYes
validFromYes
translatedYes
validUntilYes
attributionYes
sourceLocaleYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / locale / description
      Previous value: -"Language of the answer: en, fr, es, it, ar, tr, de, pt, nl, zh, ja, ko. Default en. A regional tag such as fr-FR is read as its language."New value: +"Language of the answer: en, fr, es, it, ar, tr, de, pt, nl, zh, ja, ko, pl, el, zh-TW. Default en. A regional tag such as fr-FR is read as its language."
    • changedInput schema / properties / locale / enum
      Previous value: -[
      -  "en",
      -  "fr",
      -  "es",
      -  "it",
      -  "ar",
      -  "tr",
      -  "de",
      -  "pt",
      -  "nl",
      -  "zh",
      -  "ja",
      -  "ko"
      -]New value: +[
      +  "en",
      +  "fr",
      +  "es",
      +  "it",
      +  "ar",
      +  "tr",
      +  "de",
      +  "pt",
      +  "nl",
      +  "zh",
      +  "ja",
      +  "ko",
      +  "pl",
      +  "el",
      +  "zh-TW"
      +]
    • changedOutput schema / properties / locale / enum
      Previous value: -[
      -  "en",
      -  "fr",
      -  "es",
      -  "it",
      -  "ar",
      -  "tr",
      -  "de",
      -  "pt",
      -  "nl",
      -  "zh",
      -  "ja",
      -  "ko"
      -]New value: +[
      +  "en",
      +  "fr",
      +  "es",
      +  "it",
      +  "ar",
      +  "tr",
      +  "de",
      +  "pt",
      +  "nl",
      +  "zh",
      +  "ja",
      +  "ko",
      +  "pl",
      +  "el",
      +  "zh-TW"
      +]
  2. Added

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent, closed-world), the description discloses that the card is identical for all users, is deterministic via a published SHA-256 rule seeded by the Paris date, is upright-only and today-only, that nothing is stored, and that citation plus the returned page URL is required. That is exactly the extra behavioral context annotations cannot carry.

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?

Front-loaded with the trigger and the sibling exclusion, then the payload detail. The long run-on enumeration of every returned field is somewhat over-stuffed, especially since an output schema already exists, but the information is ordered and nearly every clause carries real signal.

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?

Covers everything needed to call correctly: trigger, exclusion, determinism, timezone, upright constraint, and citation duty. The only shortfall is that the field-by-field return list duplicates the existing output schema rather than being spent on, say, failure behavior or whether the card changes at Paris midnight.

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?

The single locale parameter is fully documented in the schema (enum, default, regional-tag handling at 100% coverage). The description only adds that the card's name comes back 'in the language asked', which restates the schema's intent rather than adding new meaning; baseline 3 applies.

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?

States a specific verb and resource ('Marselia's public card of the day ... 1 upright Tarot de Marseille card for the current day in Paris') and explicitly contrasts it with marselia_draw_card, which draws for one person. An agent can select it without opening any schema.

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?

Gives an explicit trigger ('when a person asks for the tarot card of the day or today's card'), an explicit exclusion ('takes no question', 'does not draw a card for one person'), and names the alternative that handles that case. Nothing is left to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources