Skip to main content
Glama

Make a studio film

canvas_film

A studio film, at its own higher price: for when the owner wants a scripted film with voices, characters or generated footage (moving clips), not a short for a feed, which code_film makes for less. When it helps the owner choose, quote both. The writers' room writes its script, the director plans and makes it, and it opens on its own board where the owner reads the script, picks the voices and sees the plan before anything costly is made (Step through). With run false nothing is laid out or spent and the answer is the video's cost table: each part, the price at each quality and of each kind, and the script that comes first; say the total and the first step. With run true it is laid out on the canvas, commissioned, and the owner lands on its board; its script (the first step, a few thousand tokens) is written at once. run true only when the owner clearly asked to make it now. It spends the owner's tokens as the chat's same tool would: say the price before you spend.

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": {
      "goal": "<goal>"
    },
    "name": "canvas_film"
  }
}

Input Schema

NameRequiredDescriptionDefault
runNotrue makes it now: laid out on the canvas and made as a video on its own board (the script first, nothing costly before the owner's yes); false only prices it
goalYeswhat the film is for, in one line
kindNothe kind of video: moving (generated clips from first frames, talking shots with their voice), images (still pictures edited together, no generated video: less than half the price of moving) or drawn (drawn in code); moving unless the owner says
musicNoa music bed under it: always, none, or auto for Marsell to decide
soundNowho is heard: speech (the people on screen speak their lines), narration (a narrator over the picture), design (no voice; sound, music and words on screen); auto: a narrator and anyone the script gives a line
storyNothe story or context in the owner's words: what happens, where, the feeling; the writer reads it with the goal
aspectNothe film's shape; 9:16 unless the owner says otherwise
energyNohow wild the film may be; auto lets the brief decide
lengthNothe film's length in seconds; omit and Marsell decides
channelNowhere the finished film is meant to go, set as its post's place on the board; nothing is posted without the owner
contextNowho it is for and what they know: a client's brief, a meme's context, anything the writer should read
projectNoThe project's id or exact name. Optional when the account has one project.
qualityNohd (1080p, Full HD), standard (768p, only for a quick test the owner asks for; finish it in HD later keeping its takes) or 2k; hd unless the owner says
directionNoany key and value an art director would write (lighting, camera, emotions, vibe, in the style of, anything), one pair each; used beside the brand's defaults
pictureIdsNothe business's own pictures the film uses, by their file ids
productIdsNoproducts from the business's catalogue the film shows, by their ids

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare readOnly=false and destructive=false; the description adds the material behavior the agent actually needs: the owner's tokens are spent, run=false yields a cost table with per-part prices and the first-step script, and nothing costly is made before the owner's yes. The staged approval flow and 'the owner lands on its board' outcome are disclosed, which goes well beyond the annotations. It does not claim anything that conflicts with destructiveHint=false.

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 and the code_film contrast are front-loaded, then workflow, then the run-gating rule, which is a sensible order. It is dense and somewhat run-on in places ('A studio film, at its own higher price: for when...'), but for a 16-parameter tool that spends money, most sentences carry load.

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?

With 16 parameters, no output schema, and real token cost, the description covers what an agent must know to call it safely: selection vs code_film, the run=false pricing answer, the approval gate, and the resulting board. Minor gaps remain around the response shape on run=true and the project/id parameters, but the schema carries those.

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 100%, so every parameter including the seven enums is already documented; the description need only add meaning on top. It elaborates run=false vs run=true with the cost-table contents and board landing, but leaves kind, quality, sound, direction and the id lists entirely to the schema. Baseline 3 is appropriate.

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 concrete verb+resource (make a scripted studio film with voices/characters/generated clips) and immediately contrasts it with the sibling code_film ('not a short for a feed, which code_film makes for less'). An agent can distinguish the two on price and output type 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?

Gives explicit selection criteria vs the alternative ('scripted film with voices, characters or generated footage' vs 'a short for a feed'), plus a fallback ('quote both' when it helps the owner choose). It also gates the expensive path: 'run true only when the owner clearly asked to make it now' and 'say the price before you spend.'

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.