Skip to main content
Glama

Code film

code_film

A short film made in code, the default for a short for a feed (a YouTube Short, an Instagram Reel, a TikTok, a post's video): motion design, type, the business's own pictures and products, music and sound, no generated video. With run false nothing is laid out or spent and the answer is its quote: what it makes (shape, length, who reads it: say that voice, never another), what it costs at the director the owner's plan gives it, with the plan first and the film made from the plan, and the other director's price beside it; say the film's price (tokens), that the plan comes first (planFirst) and the most both together may use (mostInAll). With run true it is laid out now: the plan is written first (the only spend now) and waits on its page in Create, where the owner reads it, changes shots if they like and presses Make. run true only when the owner clearly asked to make it now. available false: films in code cannot run here now; say why, and canvas_film can make the film instead. It needs an act key, and 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>",
      "purpose": "<purpose>",
      "platform": "<platform>"
    },
    "name": "code_film"
  }
}

Input Schema

NameRequiredDescriptionDefault
runNotrue lays it out now: the plan comes first and waits on its page in Create for the owner's Make; false only prices it
goalYeswhat the film is for and what happens in it, in a few lines: the owner's ask, the trend or the offer, who it is for
energyNohow lively it is; auto lets the brief decide
projectNoThe project's id or exact name. Optional when the account has one project.
purposeYessell (a product), launch (something new), show (a story or an episode), trend (rides something trending now: find the trend first, among the Trend agent's current trends (agent_open trend) or in this week's news (web_research), and name it in the goal and to the owner), offer (a deal), laugh (a joke)
secondsNoits length in seconds, 5 to 60; omit and Marsell makes it 8 to 20 seconds
directorNohow strong a model writes and draws it: only when the owner picks one; omit and the owner's plan decides (Standard on Solo, Pro above it)
platformYeswhere it goes, which sets its shape: reels (Instagram Reels, YouTube Shorts and any tall 9:16 feed), tiktok (9:16), feed (4:5), facebook (4:5), ad (1:1), x, linkedin or wide (16:9)
productIdsNoproducts it shows, by their ids

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior5/5

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

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description discloses that it spends the owner's tokens, requires an act key, that run=false incurs no layout or spend, that run=true writes only the plan first and waits for the owner's Make in Create, and that an availability gate may block it. It even specifies how to announce price and plan-first constraints to the owner. This is unusually rich behavioral disclosure for a mutating tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is front-loaded but delivered in long, deeply nested run-on clauses such as 'what it costs at the director the owner's plan gives it, with the plan first and the film made from the plan, and the other director's price beside it'. There is no sentence or paragraph separation between the quoting path, the run path, and the availability fallback. Density obscures otherwise valuable 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 nine-parameter tool with no output schema, the description covers what the quote contains, the plan-first workflow, cost in tokens, and the availability fallback. What remains thin is what run=true returns (a work/page reference) and what an 'act key' is. Overall it is complete enough to invoke correctly.

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 description coverage is 100%, so the schema already documents run, goal, purpose, director, seconds and platform in detail. The description reinforces that trend requires finding the trend first and that director is only set when the owner picks one, but most of this duplicates the schema text. It adds little parameter meaning beyond what structured fields provide.

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?

The opening states a specific deliverable: a short feed film built from motion design, type, the business's own pictures and products, music and sound, with no generated video. It also distinguishes itself from canvas_film when the tool is unavailable. The verb is implicit ('code_film' as a noun phrase) and the tangled clause structure slows recognition, but an agent can still tell what it produces.

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?

Explicit routing is given: run=false is the default quoting path, and 'run true only when the owner clearly asked to make it now' is a clear exclusion rule. It also names canvas_film as the fallback when available=false, and tells the agent to surface the price before spending. It does not explain when to prefer this over other creation siblings (make_pictures, series_create) in the normal case.

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.