Skip to main content
Glama
Sign In

Tavern

by io.github.jakehandy
OverviewDiscussionsAdmin

Change my dice style

set_dice_style
Idempotent

Choose how your dice look: tavern (polished resin in the table's colour), bone (old ivory, the numbers cut in by hand), obsidian (black glass, flecked with gold), frost (clear ice with cold light inside, Lorekeeper), ember (coals still burning under the crust, Lorekeeper), verdigris (copper gone green, bright at the edges, Lorekeeper), grove (living wood, moss in the grain, Lorekeeper), amethyst (a cut violet stone with a light in it, Lorekeeper). The Lorekeeper styles need a Lorekeeper subscription and are refused without one. Returns: { style }.

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": {
      "style": "<style>"
    },
    "name": "set_dice_style"
  }
}

Input Schema

NameRequiredDescriptionDefault
styleYesThe style's key.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover idempotency, non-destructiveness, and closed-world scope; the description adds the refusal behavior for premium styles and the exact return shape `{ style }`. What is missing is whether the change is per-user or per-table, though 'the table's colour' hints at table context.

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, then the value catalog, then the constraint, then the return shape. The flavor text for each style is long but each phrase carries selection-relevant information, so it largely earns its space.

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 a single-parameter setter with no output schema, the description covers the value set, the error condition, and the return shape, which is nearly everything needed. Only the scope of the change (user vs. table) is left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema itself only says 'The style's key', but the description supplies the actual meaning of each enum value (resin, ivory, black glass, etc.) and tags which ones are subscription-gated. That is genuine added meaning an agent needs to pick a value sensibly.

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 ('Choose how your dice look') and resource (dice style), with the complete set of valid keys enumerated. It is clearly the write counterpart to the get_dice_style sibling and no agent could confuse the two.

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 subscription gate is spelled out precisely ('The Lorekeeper styles need a Lorekeeper subscription and are refused without one'), which is a real when-not condition. It does not explicitly name get_dice_style as the way to inspect the current style, but the context is otherwise clear.

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

All Tavern toolsInspect
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