Skip to main content
Glama

Create a character or product

create_figure

Render a four-view reference sheet from a portrait or packshot to keep recurring people or products consistent across shots and return a preview.

Instructions

Saves a recurring person or product for consistent shots: renders a reference sheet (four views) from a portrait or packshot and returns its preview. The face should be clearly visible; with flux3-edit a close-up works best. Takes about 30 to 90 s.

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": {
      "name": "<name>",
      "portrait": "<portrait>"
    },
    "name": "create_figure"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoperson
nameYesShort name used in prompts, e.g. "Mara"
outfitNoPerson: clothing for the full body view · product: details the photo does not show
portraitYesGallery id, "upload:…" ref or absolute path of the portrait or packshot
workflowNoEdit workflow that renders the sheet; default qwen21-edit for people (non-commercial), flux3-edit for products, the other one if that is not installed
wait_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
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 well: it discloses that a persistent entity is saved, that the output is a four-view reference sheet plus a preview, and gives an expected runtime of 30-90 s. It omits whether existing figures with the same name are overwritten, whether the call is billable, and how the wait_seconds parameter interacts with the stated duration.

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 sentences, no filler, with the core action and persistence benefit front-loaded before the input caveat and the latency note. Every sentence carries distinct 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 six-parameter creation tool with no annotations and no output schema, the description covers purpose, input quality constraints, output form (preview of a reference sheet) and timing. The remaining gaps are overwrite/naming behavior and cost, which are secondary but not trivial for an operation that persists state.

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 coverage is 67%, so most parameters are already documented. The description still adds real meaning for two of them: portrait quality requirements (visible face, close-up preferred) and the workflow choice (flux3-edit works best). It says nothing about name, outfit, kind, or wait_seconds, leaving the schema to do the rest.

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?

States a concrete verb-and-resource pair: saves a recurring person or product and renders a four-view reference sheet from a portrait/packshot, returning a preview. This is far more specific than the title alone, though it never explicitly distinguishes itself from siblings such as "figures" (listing) or "generate" (one-off images), so the agent must infer the boundary.

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?

Usage is conveyed indirectly through input advice ("the face should be clearly visible; with flux3-edit a close-up works best") and the phrase "for consistent shots", which implies reuse across multiple generations. There is no explicit statement of when to call this instead of "figures" or "generate", and no mention of prerequisites such as the subject having to exist in the gallery first.

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