character-forge-mcp

Overview Schema Source Related Servers Discussions Admin

Character in their environment (still)

character_scene

Draws a character in their own setting during an idle moment from a reference image, then saves the scene as the first and last frame for video generation.

Instructions

ONLY on request. Draws the character in their own place doing what they usually do (an idle moment), using concept.png as the character reference (GPT Image 2.6 edit, ≈$0.05 at medium). Saves scene.png — the first and last frame for character_video. Write a specific prompt from the card (location, idle pose, light) or omit it for a default.

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": {
      "id": "<id>"
    },
    "name": "character_scene"
  }
}

Input Schema

Name	Required	Description
`id`	Yes
`notes`	No	Corrections on top of the default prompt for this take, in plain words (e.g. 'his height must read against the ceiling', 'hands stay off the barometer'). Use this to fix a result instead of rewriting the whole prompt.
`prompt`	No	The scene: place, what they are doing, pose, light, framing. Keep the character exactly as in the reference.
`quality`	No	Default medium.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.1Nov 12, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it discloses the model (GPT Image 2.6 edit), an approximate cost (~$0.05 at medium), the fact that it writes scene.png, and that the output serves as first/last frame for character_video. It does not say whether an existing scene.png is overwritten or what happens if concept.png is missing.

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?

Dense but front-loaded — the "ONLY on request" gate comes first and every clause carries information (reference file, cost, output, consumer). The parenthetical cost/model note slightly interrupts the flow of a single long paragraph.

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 generation tool with no output schema and no annotations, it explains inputs used, artifact produced, and downstream consumer, which is enough to call it correctly. The only real gap is the precondition that concept.png must already exist and overwrite behavior on repeat runs.

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 75% and the description adds real behavior beyond it: prompt can be omitted to get a default, and the cost figure implicitly maps to the quality parameter's medium default. The id and notes parameters are left entirely to the schema, which documents them adequately.

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 — draws the character in their own place during an idle moment — and names the exact artifacts involved (concept.png as reference input, scene.png as output). This clearly separates it from siblings such as character_concept (reference creation) and character_video (which consumes scene.png).

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?

"ONLY on request" is an explicit invocation gate, and the description says to omit the prompt for a default, so the agent knows both when to call it and how to call it minimally. It stops short of naming an alternative tool when the character just needs a plain concept image.

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