Skip to main content
Glama
dearlordylord

D&D 5e SRD Oracle

Roll Dice

roll_dice

Roll ordered groups of dice for a D&D play session, returning raw face values while advancing the session's dice sequence.

Instructions

Sample an ordered, non-empty batch of structured dice groups with deterministic non-cryptographic DRDice and return visible raw faces. Each call advances the Play Session's dice sequence. This independent sampler never reads Battle Holes, derives modifiers or outcomes, or fills a Hole; copy its faces into an ordinary typed fill only when the current runtime Hole supplies the required facts.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
groupsYes
playSessionIdYesPlay Session handle returned by create_play_session for follow-up stateful calls in the same local process or authenticated account.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations are all false, so the description carries the full burden, and it delivers: deterministic non-cryptographic DRDice, advancing the Play Session's dice sequence, returning raw faces, and explicitly excluding hole-reading, derivation, and filling. No contradiction exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences with no fluff: the first states the core action, the second the side effect, the third the boundaries. Every sentence earns its place.

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?

The description is complete for this tool's complexity: independent sampling, deterministic behavior, side effect on the session, and exclusions are all present. An output schema exists for return values, so omitting a return description is fine.

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 50% because the `groups` property lacks a direct description, though its item schema details dice and dieSize. The description adds the 'ordered, non-empty batch' framing and maps to the play-session sequence, but it doesn't explain the group fields themselves. It partially compensates for the coverage gap.

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 description names a specific verb ('Sample'), a precise resource ('ordered, non-empty batch of structured dice groups'), and a clear output ('visible raw faces'). It also distinguishes itself from battle-hole and fill tools by explicitly stating it never reads Battle Holes or fills a Hole.

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?

The description gives clear when-not guidance: it never reads Battle Holes, derives modifiers/outcomes, or fills a Hole, and tells the agent to copy faces into an ordinary typed fill only when the runtime Hole supplies the required facts. It stops short of naming a specific sibling alternative, so it loses a point.

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