AstroWay Astrology API (full catalogue)

by info.astroway

Overview Discussions Admin

Marseille: Custom Spread

astroway_tarot_marseille_draw_custom

Read-onlyIdempotent

Draw 1-15 Marseille cards into positions you name or by count; seeded like the fixed spreads.

[Group: Tarot: Marseille] [Endpoint: POST /v1/tarot/marseille/draw/custom] [Cost: 10 credits (Tier 1)]

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": "astroway_tarot_marseille_draw_custom"
  }
}

Input Schema

Name	Required	Description
`art`	No	Card art set, e.g. rws-1909, rws-restored, rws-vector. GET /v1/tarot/decks lists the sets per deck.
`seed`	No
`count`	No	Number of cards when positions are not named (1 to 15).
`fields`	No	Compact mode: comma-separated dotted paths to keep, relative to `data`, e.g. "planets.name,planets.longitude,houses.cusp". Omit for the whole response.
`question`	No
`positions`	No	Your own position names, one card each, in order (1 to 15).
`precision`	No	Compact mode: round fractional numbers to this many decimals. Longitudes carry 14 by default; 2 is finer than any chart is drawn.
`allowReversed`	No

Output Schema

Name	Required	Description	Default
`back`	No
`seed`	No
`drawn`	No
`spread`	No
`question`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 7, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations already declare readOnly, non-destructive, idempotent, closed-world, so the safety profile is covered. The description adds genuine extras beyond that: a deterministic seeded draw comparable to the fixed spreads and a 10-credit Tier 1 cost, which matters for billing-aware agents. It does not say what happens when both positions and count are supplied, or what a draw with neither yields.

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?

One dense, front-loaded sentence with no filler, followed by clearly separated group/endpoint/cost metadata. Nothing is wasted, though the core sentence packs two modes together without disambiguating precedence.

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 an 8-parameter, all-optional draw tool with an output schema and annotations present, the description covers the essential mechanics (card range, custom positions, seeding, cost). The residual gap is the zero-argument default and positions/count precedence, which matters here since no parameter is required.

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 coverage is 63%; seed, question, and allowReversed have no schema descriptions. The description clarifies the positions-vs-count relationship and hints that seed makes draws reproducible, which is real added meaning, but it leaves the seed format, question usage, and allowReversed behavior unaddressed.

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?

States a specific verb and resource ("Draw 1-15 Marseille cards") plus the distinguishing feature versus the fixed spreads: positions the caller names, or a raw count. An agent can tell this apart from draw_three_card or draw_celtic_cross. It stops short of naming those siblings explicitly.

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?

"positions you name or by count" implies the two usage modes, but there is no explicit guidance on when to choose this over a named spread or which sibling lists the built-in spreads. The agent must infer the boundary from the tool name and the phrase 'custom'.

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

All AstroWay Astrology API (full catalogue) 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?