Skip to main content
Glama

RFWIN: provably fair winner draws

draw_winners

Perform a verifiable random draw (commit-reveal + drand) of winners from contestants and prizes. Saves a proof page on rfwin.uk/d/:id. Free for all accounts (free tier: up to 10,000 contestants per draw; paid plans: larger draws). Optional radio preset: alternates (ordered backup winners), station, show. Optional visibility: "public" (default, indexable) or "private" (unlisted: works and verifies for anyone with the link, but noindex and never listed).

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": {
      "contestants": "<contestants>",
      "prizes": "<prizes>"
    },
    "name": "draw_winners"
  }
}

Input Schema

NameRequiredDescriptionDefault
showNoOptional show or segment name shown on the proof page.
titleNoOptional title for the draw
prizesYesList of prizes and quantities to draw for
stationNoOptional station name / call sign shown on the proof page.
algorithmNoDrawing algorithm: random (equal weight) or weighted. Default random.
alternatesNoOptional number of ordered backup winners (0-20) drawn after the main prizes, e.g. for radio giveaways. Requires uniqueWinners.
visibilityNoOptional. "public" (default): proof page is indexable by search engines. "private" (alias "unlisted"): proof page works and verifies for anyone with the link (get_draw / verify_draw too) but is noindex,nofollow and never listed.
contestantsYesList of contestants (names, emails, or usernames)
uniqueWinnersNoIf true, a contestant can win at most one prize. Default true.

Output Schema

NameRequiredDescriptionDefault
drawIdNo
winnersNo
visibilityNo
manageTokenNoOrganiser token for PATCH https://rfwin.uk/api/draws/{id}/visibility (header X-RFWIN-Manage-Token). Keep private.
verificationUrlNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden, and it does disclose the verification mechanism, the persisted proof page and its URL pattern, tier limits, and the indexing consequences of each visibility setting. It does not cover failure modes, whether a draw consumes credits or is rate-limited, or whether an existing draw can be superseded — meaningful gaps for an irreversible mutation.

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 purpose and mechanism, then limits, then optional knobs — a sensible order with no filler sentences. It loses a point for restating the visibility enum almost verbatim from the schema, which duplicates rather than adds.

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?

An output schema exists, so return values need not be described; the description instead covers the mechanism, persistence, and access tiers that an agent needs before triggering a draw. For a 9-parameter mutation with no annotations, the missing piece is operational risk (reversibility, rate/cost limits) rather than parameter understanding.

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 100%, so the schema already documents every parameter including the visibility enum and alternates. The description adds one genuine cross-parameter constraint not in the schema (alternates requires uniqueWinners) and explains why alternates exist (ordered backups for radio giveaways), but it never mentions algorithm or uniqueWinners semantics itself, so it is only marginally above baseline.

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 ('perform a verifiable random draw of winners from contestants and prizes') plus the mechanism (commit-reveal + drand) and a concrete side effect (saves a proof page at rfwin.uk/d/:id). This is clearly the draw-creating tool, distinguishable from get_draw and verify_draw by name and behavior.

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 practical selection context: free tier caps at 10,000 contestants per draw while paid plans allow larger, and it explains the public vs private visibility tradeoff so an agent can choose appropriately. It never explicitly says when to prefer this over get_draw/verify_draw, but the create-vs-inspect split is obvious from the stated purpose.

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