VALUE Verdicts

Situated draw (verifiable cards for a place and intent)

situated_draw

Read-only

Draws 1-10 ROAST-78 cards for a world tile and an optional intent, using the public drand beacon (League of Entropy, including Cloudflare; a new BLS-signed value every 3 s). Nobody, including this service, can steer the outcome before the beacon round is published, and anyone can replay it from the receipt (round + tile + intent hash). Positions are named from the place card's own spread template when one exists for that count. Each card includes orientation, meaning, keyword, element, story catalyst and prompt. The intent text is hashed, never stored or returned. Price: $0.01 USDC per call after 25 free calls per day.

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": {
      "latitude": "<latitude>",
      "longitude": "<longitude>"
    },
    "name": "situated_draw"
  }
}

Input Schema

Name	Required	Description
`at`	No	Optional past UTC instant (e.g. 2026-11-02T08:30Z) to draw with the beacon round of that moment. Omit for now.
`count`	No	Optional number of cards, 1 to 10 (default 1).
`round`	No	Optional drand round, to replay or verify an earlier draw. Omit for a fresh, unpredictable draw.
`intent`	No	Optional question or intent (max 500 characters). Only its SHA-256 hash is used and returned.
`_payment`	No	x402 v2 payment: base64 PaymentPayload, as you would send in the PAYMENT-SIGNATURE header. Only needed after the free allowance is used.
`latitude`	Yes	Latitude from -90 to 90.
`longitude`	Yes	Longitude from -180 to 180.
`reversals`	No	Optional. Allow reversed cards (default true).

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 1, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Goes well beyond readOnlyHint/openWorldHint: it discloses the randomness source and its cadence, that the service cannot steer the outcome, that any draw is replayable from a receipt (round + tile + intent hash), that intent text is hashed and never stored or returned, and the pricing model. These are exactly the traits an agent needs to trust and cost-plan a call.

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?

Purpose is front-loaded in the first clause and every following sentence carries operational weight (verifiability, privacy, price). The drand parenthetical naming League of Entropy, Cloudflare and the 3-second BLS cadence is slightly ornamental for tool selection but supports the verifiability claim.

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?

With no output schema, the description does the work of describing returns (orientation, meaning, keyword, element, story catalyst, prompt) plus privacy, cost, and verification. Minor gaps remain: what happens when no spread template exists for that count, and error/payment-failure behavior.

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 100%, so the schema already documents all eight parameters and the baseline is 3. The description adds real meaning on top: positions derive from the place card's spread template depending on count, intent is hashed rather than stored, and draws are reproducible via round — context the schema does not supply.

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?

The opening sentence gives a specific verb (draws), a specific resource (1-10 ROAST-78 cards), and the two scoping inputs (world tile, optional intent). No sibling tool (celestial_*, location_context, address_check) does anything comparable, so an agent can select this unambiguously.

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?

Usage context is implied rather than stated: the description explains fresh vs. replay draws and the metering threshold (25 free calls then $0.01 USDC), but the explicit 'omit for a fresh draw / use round to replay' guidance lives in the schema fields, not the description. No alternatives or when-not-to-use conditions are named against siblings.

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

All VALUE Verdicts 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?