Tavern

Add a custom item

add_custom_item

Put something in the character's Inventory that the sheet doesn't have. A sync never touches it. Returns: The item.

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_custom_item"
  }
}

Input Schema

Name	Required	Description
`cost`	No	Value.
`icon`	No	A glyph key from the app's icon set.
`name`	No	What it is called.
`slot`	No	Where it is worn, for equipment.
`armor`	No	Armor numbers.
`magic`	No	Whether it is magical.
`detail`	No	The whole text.
`rarity`	No	How rare it is.
`weight`	No	Weight.
`acBonus`	No	Armor class it adds while worn.
`effects`	No	Up to eight effect lines.
`summary`	No	One line for the card.
`campaign`	Yes	The campaign, by its slug (what its link says) or its id.
`itemType`	No	A short type line, in your own words.
`quantity`	No	How many.
`statLine`	No	A stat line for the card.
`character`	Yes	The character, by its slug.
`equipment`	No	True for something worn or wielded, false for counted gear.
`requiresAttunement`	No	Whether it needs attuning.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the mutation profile is known without the description. The description adds genuine value beyond that by promising the item survives syncs and by stating the return value ("Returns: The item"). It does not warn that non-idempotent repeated calls duplicate entries, nor what happens if the character slug is invalid.

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 core action, then the persistence guarantee, then the return value. Nothing is padded or redundant, and an agent can read the whole thing in one pass.

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?

For a 19-parameter mutation tool with a nested armor object and no output schema, the description covers the action, the sync-exemption behavior, and the return shape, which is the minimum viable set. It is thin on the operational side: no permission or ownership requirements, no duplicate-handling note, and no hint about how the equipment/slot/armor fields interact with the boolean equipment flag.

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% across all 19 parameters, including enums for slot and armor.kind and bounds on acBonus, quantity, effects, and name length, so the schema does the heavy lifting. The description contributes no parameter meaning at all — nothing about which fields matter for equipment versus counted gear. 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?

"Put something in the character's Inventory that the sheet doesn't have" gives a specific verb plus resource and a scope qualifier that separates it from sheet-derived items. The sibling set includes update_custom_item and sync_character, and while the description implies it is the creation counterpart to update, it never names update_custom_item explicitly, so differentiation is inferred rather than stated.

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

Usage Guidelines3/5

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

The qualifier "that the sheet doesn't have" is a usable when-condition, and "A sync never touches it" signals the persistence guarantee versus synced data. However, there is no guidance on the add-vs-update decision (update_custom_item exists as a sibling), no mention that repeat calls are non-idempotent and will create duplicates, and no stated prerequisites such as permissions or character ownership.

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.