Sairen

random_decision_oracle

Generate cryptographically secure random outcomes to eliminate LLM token prediction bias. Use coin flips, dice, cards, numbers, and chance checks for fair decisions in games, arbitrations, and simulations.

Instructions

    [Cost: $0.0001 USDC on Base & Solana] Master cryptographically secure CSPRNG decision oracle & entropy engine.
    Eliminates LLM token prediction bias (e.g., >65% bias on 'heads') in games, arbitrations, simulations, and stochastic branching.

    Actions & Parameters:
    - 'coin': Flips fair or weighted coins. Params: {"flips": 1..1000, "p_heads": 0.0..1.0}
    - '8ball': Consults canonical 20-outcome Magic 8-Ball. Params: {"question": "..."}
    - 'fortune': Cracks fortune cookie with aphorism & lucky numbers. Params: {"theme": "all"|"crypto"|"algorithmic"}
    - 'number': Generates random numbers. Params: {"min": 1, "max": 100, "count": 1, "unique": true}
    - 'chance': Evaluates probability threshold check. Params: {"threshold": 0.0..100.0}
    - 'rps': Plays Rock-Paper-Scissors / Lizard-Spock. Params: {"player_move": "rock", "variant": "classic"|"rpsls"}
    - 'dice': Rolls polyhedral RPG dice notation. Params: {"notation": "2d6+3"|"1d20"|"4d6d1"}
    - 'card': Draws playing cards from standard 52-card deck. Params: {"count": 1..52}
    - 'pick': Weighted or uniform item selection. Params: {"items": ["a","b"], "count": 1, "weights": [1,2]}
    - 'token': Generates cryptographically secure nonces or UUIDs. Params: {"token_type": "uuid4"|"hex", "byte_length": 16}

Input Schema

TableJSON Schema

Name	Required	Default
`action`	No	coin
`params`	No
`payment_signature`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.3.0Sep 25, 2026

TDQS

A3.7/5.0

Behavior3/5

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

No annotations are provided, so the description carries the burden. It discloses the $0.0001 USDC cost, cryptographic security, and the full action set. However, it does not explain the payment_signature parameter, whether payment is required before invocation, or failure behavior, which are important for a paid tool.

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?

The description is long but well-structured: cost and purpose first, then a compact action/parameter list. No filler, though the list is extensive.

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

Completeness3/5

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

The description covers the action/parameter space well and an output schema exists, so return values are covered. The missing payment_signature semantics and lack of error/edge-case guidance leave an agent uncertain about how to invoke a paid tool correctly.

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%, and the description compensates strongly by documenting each action's parameters with types/ranges/examples. It does not document the top-level payment_signature parameter, which is a notable gap.

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 clearly identifies the tool as a cryptographically secure random decision/entropy oracle and enumerates its concrete actions (coin, 8ball, fortune, number, chance, rps, dice, card, pick, token). It distinguishes it from sibling tools by its randomness/entropy function, though it is a multi-action tool rather than a single verb+resource.

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?

It provides clear use context: eliminating LLM token prediction bias in games, arbitrations, simulations, and stochastic branching. It does not explicitly state when not to use it or name alternatives, but the context is specific enough to guide selection.

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

Deploy Server