Skip to main content
Glama

draw_character

Create simple custom characters in the current style's format and add them to a library or shot; invalid drawings are validated and refused with a reason.

Instructions

Draw a new character yourself, free, in the current style's format, and add it to the person's library and into a shot. Use it for simple characters the style doesn't have; for a photo-like picture use generate_character (paid). No Claude usage or credits are spent: you send the drawing as plain data and Dinoctor checks it (bad fields are dropped; a drawing that fails is refused with the reason). Call describe_drawing first for the exact format. Formats in short: Pixel = {"name","rows":["..##..",...],"colors":{"#":"#535353"},"eyes":[[col,row]],"mouth":[col,row]} (up to 28x28, '.' empty, facing right, at least 20 columns wide); Toon = {"name","skin","shirt","pants","hair":"tuft|bob|ears|antennae|cap|horns|none","hairColor","snout","tail","wide","tall"}; Voxel = {"name","boxes":[{"at":[x,y,z],"size":[w,h,d],"color","part":"body|legL|legR|armL|armR"}],"eyes","mouth","faceZ"}; other styles have their own format (describe_drawing). Places in every style: {"name","sky","horizon","floor","dark","stars","clouds","orb","items":[{"kind","x","z","size"}]}. Returns the new id. Then use look to check it.

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": {
      "drawing": "<drawing>"
    },
    "name": "draw_character"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNoLeft to right, about -6 to 6. Empty spaces it automatically.
shotNoShot index from 0 in that scene.
sizeNo1 is normal.
sceneNoScene index from 0. With no shotId/scene, the shot on screen is used.
shotIdNoThe shot's id (from get_project).
drawingYesONE drawing object in the style's format (not an array).
addToShotNofalse only saves it to the library. Default true: it joins the shot's cast.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Goes well past the annotations by disclosing cost behavior ("No Claude usage or credits are spent"), the validation contract ("bad fields are dropped; a drawing that fails is refused with the reason"), the return value ("Returns the new id"), and the default side effect (addToShot true joins the shot's cast). The annotations only state it is not read-only and not destructive; the description supplies the operational consequences.

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?

Purpose, alternative, cost, and prerequisite are front-loaded before the format detail, and the dense prose is largely justified. The inline format dump is somewhat redundant with the instruction to call describe_drawing first for the exact format, which inflates length without adding new information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter tool with a nested free-form drawing object and no output schema, the description covers input shape, validation failure mode, return value, and the recommended verification step. Nothing an agent needs to call it correctly is missing.

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 baseline is 3, but the description adds real meaning for the required drawing parameter by spelling out per-style shapes (Pixel rows/colors/eyes/mouth with the 28x28 and 20-column constraints, Toon fields and hair enum values, Voxel boxes, and the shared place schema). The other six parameters (x, size, scene, shot, shotId, addToShot) get no description-level elaboration, so it stops short of a 5.

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?

Opens with a specific verb+resource ("Draw a new character yourself ... add it to the person's library and into a shot") and immediately contrasts itself with the sibling generate_character for photo-like output. An agent can pick between the two without opening either schema.

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

Usage Guidelines5/5

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

Explicit when-to-use ("simple characters the style doesn't have"), explicit when-not plus named alternative ("for a photo-like picture use generate_character (paid)"), a prerequisite ("Call describe_drawing first for the exact format"), and a follow-up step ("Then use look to check it").

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