Skip to main content
Glama
Sign In
character-forge-mcp

character-forge-mcp

by gdhub-io
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Start a new character

character_create
Read-only

Starts a character from nothing, a brief, or a concept image by rolling coherent story engines and surprising sparks, defaulting to three competing variants for a variant tournament.

Instructions

The one way to start a character, from whatever the user gave: nothing (random), a text brief, a concept image, or a concept image plus a brief. Rolls coherent ENGINES (wound → lie → fear → worst trait / best trait → truth → arc) plus surprising SPARKS — by default 3 competing variants of the same concept for the variant tournament — and says how to treat the brief and the image. Same seed = same roll.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "character_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNoReproduce a previous roll.
briefNoThe user's description of the character, verbatim, if they gave one.
genreNoFix the genre instead of rolling it.
anchorNoRole every variant shares, e.g. 'fisherman', 'court jester', 'mascot for a bakery'.
mediumNoFix the medium instead of rolling it.
conceptNoPath or URL of the user's own concept image, if they gave one. It becomes the winner's concept instead of a generated one.
settingNoFix the setting instead of rolling it.
variantsNoHow many competing variants. Default 3 (the tournament); 1 only when the user asks for one quick character.
allow_nonhumanNoAllow non-human species. Default true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare readOnlyHint, so the description must carry the rest, and it does: it discloses the internal generation chain (wound → lie → fear → trait → truth → arc), that sparks are included, that 3 competing variants are rolled by default, that the result explains how to treat the brief/image, and that seeds are reproducible. Missing only what the shape of the returned payload looks like, which is partly implied by 'says how to treat the brief and the image.'

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?

Front-loaded with the single most decision-relevant fact (this is the only way to start a character) before any mechanism detail. It is dense with coined vocabulary (ENGINES, SPARKS, variant tournament) that costs a little decoding, but nearly every clause conveys actionable information rather than filler.

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 nine-parameter, mutation-adjacent tool with no output schema, the description covers input modes, the default variant count, seed reproducibility, and the fact that the response includes guidance text. The main residual gap is whether anything is persisted given the readOnly hint, which the description leaves to inference from the sibling split.

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

Parameters4/5

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

Schema coverage is 100%, so the schema already documents all nine parameters and the baseline is 3. The description still adds value by reinforcing the two defaults that matter most (variants=3 tournament, same seed = same roll) and by framing brief and concept as 'whatever the user gave', tying them to the input-mode decision.

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 and resource ('start a character') and immediately enumerates the four input shapes it accepts (nothing/random, brief, concept image, image plus brief), which lets an agent map whatever the user supplied onto a call. It also implicitly separates itself from the persistence siblings by being 'the one way to start' rather than to save, fetch, or list.

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?

Explains the selection condition for input modes ('whatever the user gave') and gives an explicit deviation rule: keep the default 3 variants except when 'the user asks for one quick character.' It stops short of naming a sibling or stating when not to use this tool, but 'the one way to start a character' makes the entry-point role unambiguous.

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

Deploy Server

Other Tools