Tavern

Make a character here

create_custom_character

Build a character from your own answers in one call: the guided creator's questions, sent at once. Labels are yours (species, class and the rest are free text); the app works out the arithmetic. A player's new character becomes theirs and their primary. Returns: The new character's slug.

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>",
      "name": "<name>",
      "heritage": "<heritage>",
      "classes": "<classes>"
    },
    "name": "create_custom_character"
  }
}

Input Schema

Name	Required	Description
`ac`	No	Armor class.
`name`	Yes	The character's name. Required to finish.
`boxes`	No	What they can do, as Actions cards.
`items`	No	What they carry.
`maxHp`	No	Maximum hit points.
`speed`	No	Speed in feet.
`senses`	No	Senses.
`classes`	Yes	Classes and levels, at least one, each with a name and a level of 1 or more. Required to finish.
`hitDice`	No	Hit dice.
`campaign`	Yes	The campaign, by its slug (what its link says) or its id.
`heritage`	Yes	What they are, in your table's words (species, ancestry, lineage). Required to finish.
`abilities`	No	The six ability scores.
`avatarUrl`	No	A portrait's web address.
`background`	No	Where they come from.
`immunities`	No	Immunities.
`initiative`	No	Initiative bonus.
`resistances`	No	Resistances.
`vulnerabilities`	No	Vulnerabilities.
`proficiencyBonus`	No	Proficiency bonus.
`passivePerception`	No	Passive perception.
`saveProficiencies`	No	Saving throws they are proficient in.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare a non-read-only, non-idempotent, non-destructive write with no open-world access. Beyond that, the description adds genuine value by disclosing the ownership side effect (the character becomes the player's and their primary) and the return value (the new character's slug). It does not cover failure modes, whether campaign membership is required, or what happens to partially invalid nested data.

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 and the 'one call' qualifier, then constraints, then the return value. Nothing is redundant and the ordering matches how an agent needs the information.

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 21-parameter tool with deep nested objects and no output schema, the description covers the essential framing: free-text labels, server-side arithmetic, ownership outcome, and the returned slug. Gaps remain around campaign preconditions and validation behavior on the nested items/boxes arrays.

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 baseline is 3. The description does add real meaning: it clarifies that heritage, class and other labels are free text rather than enumerations, and that derived values are computed by the app rather than supplied. That is useful framing but not parameter-level detail beyond the schema.

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 names a specific verb and resource ('Build a character') and adds a distinguishing scope marker: it is done 'from your own answers in one call,' which separates it from a multi-step draft flow. It never names the sibling it replaces, though, so an agent must infer the boundary with start_character_draft, finish_character_draft, and add_character_from_beyond.

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?

'In one call: the guided creator's questions, sent at once' implies the condition for use (you already have all answers), but no alternative is named and no exclusion is stated. An agent can infer the draft-flow distinction but is not told explicitly when to prefer one over the other.

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.