Skip to main content
Glama

AskY Tarot Reading

Tarot reading

get_tarot_reading

Draws four Tarot de Marseille cards (Major Arcana) for one question and returns AskY's written reading of them: the cards, what each one says, how they read together, a piece of advice and a question to take away. Use when someone asks for a tarot reading about a question of their own. Pass only the question itself, not the conversation. Questions about a medical diagnosis, death, gambling, harming someone, or from someone in crisis are not read: the tool returns a supportive message or a gentler question instead of cards. The question is used only to write the reading and is then erased; the number of readings depends on what the person's account includes; when it is reached the tool says so. Requires the person to be signed in to their AskY account; the reading is saved to that account.

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": "get_tarot_reading"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoLanguage of the answer: "en" for English, "es" for Spanish. Use the language the person is writing in. Defaults to English.
nameNoOptional first name to address the person by, only if they gave it.
topicNoWhat the question is about: love, work, health (health and wellbeing), friendship, or life (personal growth). Optional; leave out if unsure.
questionYesThe person's question, in their own words. One question, 3 to 1500 characters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations it discloses material behavior: authentication is required (signed-in AskY account), the reading is persisted to that account, the question text is used only to generate the reading and then erased, and the number of readings is quota-limited with the tool reporting when the limit is reached. It also warns that for prohibited topics the tool returns a supportive message or gentler question instead of cards — an output-shape exception an agent must anticipate. All of this is consistent with readOnlyHint=false and idempotentHint=false.

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?

It is front-loaded with what the tool does, then usage, exclusions, privacy/quota, and auth, and nearly every sentence carries operationally relevant content. The single dense paragraph is slightly long and would scan faster broken into short lines, but there is no filler.

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

Completeness5/5

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

There is no output schema, and the description compensates by describing the reading's components and the non-card refusal path, so an agent knows what to expect back. Authorization, privacy, and quota behavior round out what an agent needs before calling; nothing essential is missing for a single-question generative tool.

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 100%, so all four parameters (question, lang, name, topic) are already documented with enums, lengths, and defaults; that establishes the baseline of 3. The description contributes only one extra constraint beyond the schema — pass the question alone, not the conversation — with no added detail on lang, name, or topic.

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 names a specific verb and resource — draws four Tarot de Marseille (Major Arcana) cards for one question — and enumerates the returned reading's parts (cards, per-card meaning, synthesis, advice, takeaway question). It does not explicitly contrast itself with siblings like get_card_of_the_day or get_card_meaning, leaving that differentiation to be inferred from the names.

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?

It states when to use it ('when someone asks for a tarot reading about a question of their own') and gives an explicit when-not list: medical diagnosis, death, gambling, harming someone, or a person in crisis, plus what happens instead. It also constrains invocation input ('Pass only the question itself, not the conversation'), which is actionable routing guidance.

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