Marselia

Tarot Advent calendar card

marselia_advent_card

Read-onlyIdempotent

A day of Marselia's tarot Advent calendar (1 to 24 December): 1 upright Tarot de Marseille card a day, the same for everyone, drawn by a published SHA-256 rule (24 different cards), with the validated card-of-the-day text in the language asked, the card plate URL (public domain BnF scan, show it whole in its 440:827 frame), the card page, the Marselia Academy lesson to learn it and the calendar page. Day 1 to 24, default today (Paris time). A day opens on its own Paris day: an earlier request answers that it is not open yet, and no future card is ever given. A theme for the day, never a prediction. Free, takes no question. Cite Marselia and the calendar 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_advent_card"
  }
}

Input Schema

Name	Required	Description	Default
`day`	No
`locale`	No		en

Output Schema

Name	Required	Description	Default
`day`	Yes
`url`	Yes
`card`	Yes
`draw`	Yes
`year`	Yes
`phase`	Yes
`today`	Yes
`locale`	Yes
`drawUrl`	Yes
`opensOn`	Yes
`openDays`	Yes
`attribution`	Yes
`archiveUntil`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 6, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses the deterministic SHA-256 selection rule, that all users get the same card, that 24 distinct cards appear, timezone-scoped availability (Paris day) and the exact failure behavior for early requests ('not open yet'). It also states the citation obligation and the 440:827 display constraint for the plate image — behavior an agent could not infer from annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded, but the body is one long comma-chained sentence mixing returns, gating rules, citation policy and image framing. Some content earns its place (the Paris-day gating), while 'Free, takes no question' and the return-item list partially duplicate the output schema and could be tightened.

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 two-param read tool with an output schema and safety annotations, the definition covers availability rules, determinism, defaults and citation requirements adequately. Remaining gaps are the locale fallback behavior and whether the linked lesson is localized to the same locale — both relevant to how an agent should call it and report results.

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?

Schema coverage is 0%, so the description must carry parameter meaning: it documents the day range (1-24) and the un-schema'd default of 'today' with its Paris timezone basis, plus that the text is returned in the requested language. Locale handling is thinner — the 12 enum values and any fallback for a language without validated text are never addressed.

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+resource: retrieve one day (1-24 December) of Marselia's tarot Advent calendar, with an explicit enumeration of what comes back (card text, plate URL, card page, Academy lesson, calendar page). The clauses 'the same for everyone', 'drawn by a published SHA-256 rule' and 'takes no question' separate it from the sibling drawing/search tools without naming them.

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

Usage Guidelines4/5

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

Gives clear operating context: day range, default to today in Paris time, free, no question taken, and the rule that a day is only retrievable on its own Paris day with no future cards ever returned. It does not explicitly name marselia_draw_card or marselia_get_card as the alternative when a user wants a personal/question-based draw, so routing relies on inference from 'takes no question'.

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

All Marselia tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?