Tavern

Add a homebrew card

add_homebrew_box

Add a card to the character's Actions: an ability, a trick, a boon. A sync never touches it. Returns: The card.

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": {
      "campaign": "<campaign>",
      "character": "<character>"
    },
    "name": "add_homebrew_box"
  }
}

Input Schema

Name	Required	Description
`cost`	No	What using it takes.
`dice`	No	A roll it makes that isn't an attack, like 1d8+2.
`icon`	No	A glyph key from the app's icon set. Unknown keys fall back to the default.
`name`	No	What it is called. Required.
`save`	No	A saving throw it forces.
`uses`	No	Limited uses, if it has any.
`attack`	No	An attack roll, if it makes one.
`detail`	No	The whole text, for the drawer.
`summary`	No	One line for the card.
`campaign`	Yes	The campaign, by its slug (what its link says) or its id.
`character`	Yes	The character, by its slug.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations declare non-readonly, non-destructive, non-idempotent, but the description adds two non-obvious facts: the card survives character sync ('A sync never touches it') and the call returns the created card. It stops short of warning that repeat calls will create duplicates (consistent with idempotentHint=false) or describing failure modes for bad slugs.

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 short sentences, front-loaded with the action, then the persistence note, then the return value. No filler, nothing redundant with structured fields.

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 an 11-parameter tool with nested objects, the description covers purpose, persistence behavior, and return value while the schema carries all field semantics. Minor gaps remain around duplicate creation and validation failures, but nothing critical to calling it correctly is missing.

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 description coverage is 100%, so the schema already explains every parameter including the nested attack/save/uses objects. The description adds only the illustrative examples of card kinds, not meaning for campaign/character slugs or the enum'd cost field; baseline 3 applies.

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?

"Add a card to the character's Actions" gives a specific verb plus target and clarifies the jargon ('an ability, a trick, a boon'). It implicitly pairs with the sibling update_homebrew_box (add vs. modify) but never names it, so the agent must infer the distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use or when-not-to-use guidance. With siblings like update_homebrew_box and add_custom_item present, the agent gets no rule for choosing between creating a new homebrew entry versus updating an existing one, nor any stated prerequisites (e.g., character must exist, permissions).

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

All Tavern 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.