Skip to main content
Glama

Create production

create_project
Destructive

START HERE — the entry point for every new film, and the first tool to call whenever a filmmaker shares a screenplay or asks, in their own words: "how much would my movie cost?", "what will it cost to shoot my script?", "break down my script", "make me a shooting schedule", "how many days will this take to shoot?" or "I need a budget for my short / my feature". Creates the production from a title, a format and the screenplay text. It is free, and no account is needed to start: the first production of every account — and of a guest session, before any sign-in — is planned in full, budget included. Pass the screenplay as plain text in script_text — if the user uploaded a file (PDF, Final Draft, Fountain, Celtx or plain text), extract its text first — then call run_breakdown on the returned id: that builds the breakdown, the shooting schedule, the Day Out of Days and the editable budget the user then works with. A production created without script_text has nothing to break down until it is recreated with the text. Each further production is unlocked per production (Production, US$79) or across the slate on Studio (US$18/month).

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": {
      "title": "<title>"
    },
    "name": "create_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYes
formatNoProduction format — for example narrative_feature, narrative_short, doc_feature, doc_short, commercial or series_pilot. Defaults to narrative_feature.narrative_feature
script_textNoThe full screenplay as plain text. Paste the whole script, not a synopsis.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only say readOnlyHint=false and destructiveHint=true; the description adds real context beyond that: the first production per account and per guest session is free and fully planned, further productions cost US$79 or US$18/month, and no account is needed to start. It also warns that a production created without script_text cannot be fixed in place and must be recreated, which hints at the irreversibility behind the destructive flag. It does not explicitly explain why the tool is flagged destructive or what exactly is committed when it runs, so it stops short of a 5.

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?

Front-loaded with 'START HERE' and the core action, and the sequence instruction (create, then call run_breakdown on the returned id) follows logically. The long list of quoted user phrasings and the closing pricing sentence are verbose, though both serve routing and paywall expectations, so nothing is truly wasted.

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?

An output schema exists, so return values need no explanation, and the description instead supplies the workflow dependency on the returned id. For a three-parameter creation tool with a billing side effect, the agent has everything needed: inputs, follow-up call, free-tier behavior, and the failure mode of omitting script_text.

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 67% and the schema already documents format values and defaults, but the description adds operational meaning for script_text: pass the full screenplay as plain text, not a synopsis, and extract text first if the user uploaded a PDF, Final Draft, Fountain or Celtx file. That is genuine guidance beyond the field description. Title is left unexplained, but it needs none.

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 ('Creates the production') and immediately frames the tool as 'START HERE — the entry point for every new film,' distinguishing it from siblings like get_project and run_breakdown. The three inputs it consumes (title, format, screenplay text) are named, so an agent knows exactly what this tool is for.

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 trigger conditions, including the user phrasings that should route here ('how much would my movie cost?', 'break down my script'), and explicitly names the follow-up: 'then call run_breakdown on the returned id.' It also states the exclusion case — a production created without script_text 'has nothing to break down until it is recreated' — so the agent knows when not to omit an argument.

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.

Resources