Skip to main content
Glama

Prepare videos (quote)

create_project

Step 1 of 2: nothing is charged. Creates a draft project from a website URL and/or a brief with your settings (goal: a preset, or custom with a one-line goal_description of the user's own goal; platform, aspect, duration, pace (calm, normal or fast; default: the goal's), tier, resolution, language, voice, music, quantity, Brand Kit), starts the free site analysis when a URL is given, and returns a quote: quote_id, credits per video and in total, balance after. Show the quote to the user; only after they approve that exact amount, call confirm_operation(quote_id). Quotes expire after 30 minutes. Language: the one you pass always wins; without it the films follow the analysed site's language (applied once the analysis is read, at the latest at confirm_operation), else the brief's, with a native voice of that language.

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": "create_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoWebsite or product page to analyse (free).
goalYessales, signups, app_installs, launch, awareness, explainer or retarget; or custom, with goal_description (the user's own goal).
lookNoThe film's look: auto (default, picked from your brand) or a style family: editorial-paper, dark-tech, playful, luxe-editorial, bold-retail, soft-gradient, brutalist-grid, organic-illustrated (get_options describes each).
paceNoThe film's pace: calm (Calm), normal (Balanced) or fast (Punchy); get_options paces describes each. Default: fast (Punchy) for every goal. Same price; a Calm or Balanced film's default music follows its pace.
tierNoDeprecated: use quality. t1 / t2 = standard, t3 = studio.
briefNoWhat to say: product, audience, offer, angle. Required (20+ characters) without a url.
titleNo
aspectNo
qualityNostandard (default) or studio: one rate per second each (get_options qualities).
captionsNoBurned-in subtitles of the voice-over (default off: the video already shows its key words on screen).
languageNoThe films' language (voice-over, on-screen text, title). Default: the analysed site's language (with a url: applied when the analysis is done, at the latest when the quote is confirmed), else the brief's, else en. A language given here always wins.
platformNoWhere it runs; sets the default aspect and safe zones.
quantityNoIndependent variants of the same brief (plan maximum in get_options).
voice_idNoA voice id from get_options; default: one that suits the goal, a native speaker of the language where we have one.
music_moodNo
resolutionNo1080p
visibilityNoDefault: the account setting (public in the gallery unless changed).
brand_kit_idNoFrom list_brand_kits; default: the account's default kit.
duration_secondsNo
goal_descriptionNoWith goal custom (required then): the user's own goal in one line, ≤ 140 characters — what viewers should do after watching ("Book a free 15-minute call with our team"). The script, pacing and call to action are written for it.
review_storyboardNoPause after each storyboard for approve_storyboard (default false: confirm_operation is the only approval; each video is storyboarded, voiced and rendered in one go, and still pauses if its price would exceed the quote).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / pace / description
      Previous value: -"The film's pace: calm (Calm), normal (Balanced) or fast (Punchy); get_options paces describes each. Default: the goal's (explainer calm; launch and awareness fast; the others normal). Same price; a Calm or Balanced film's default music follows its pace."New value: +"The film's pace: calm (Calm), normal (Balanced) or fast (Punchy); get_options paces describes each. Default: fast (Punchy) for every goal. Same price; a Calm or Balanced film's default music follows its pace."
  2. Changed1 schema field changed
    • addedInput schema / properties / review_storyboard
      Added value: +{
      +  "description": "Pause after each storyboard for approve_storyboard (default false: confirm_operation is the only approval; each video is storyboarded, voiced and rendered in one go, and still pauses if its price would exceed the quote).",
      +  "type": "boolean"
      +}
  3. Changed1 schema field changed
    • addedInput schema / properties / pace
      Added value: +{
      +  "description": "The film's pace: calm (Calm), normal (Balanced) or fast (Punchy); get_options paces describes each. Default: the goal's (explainer calm; launch and awareness fast; the others normal). Same price; a Calm or Balanced film's default music follows its pace.",
      +  "enum": [
      +    "calm",
      +    "normal",
      +    "fast"
      +  ],
      +  "type": "string"
      +}
  4. Changed6 schema fields changed
    • changedInput schema / properties / goal / description
      Previous value: -"sales, signups, app_installs, launch, awareness, explainer or retarget"New value: +"sales, signups, app_installs, launch, awareness, explainer or retarget; or custom, with goal_description (the user's own goal)."
    • changedInput schema / properties / goal / enum
      Previous value: -[
      -  "sales",
      -  "signups",
      -  "app_installs",
      -  "launch",
      -  "awareness",
      -  "explainer",
      -  "retarget"
      -]New value: +[
      +  "sales",
      +  "signups",
      +  "app_installs",
      +  "launch",
      +  "awareness",
      +  "explainer",
      +  "retarget",
      +  "custom"
      +]
    • addedInput schema / properties / goal_description
      Added value: +{
      +  "description": "With goal custom (required then): the user's own goal in one line, ≤ 140 characters — what viewers should do after watching (\"Book a free 15-minute call with our team\"). The script, pacing and call to action are written for it.",
      +  "maxLength": 560,
      +  "type": "string"
      +}
    • removedInput schema / properties / language / default
      Removed value: -"en"
    • addedInput schema / properties / language / description
      Added value: +"The films' language (voice-over, on-screen text, title). Default: the analysed site's language (with a url: applied when the analysis is done, at the latest when the quote is confirmed), else the brief's, else en. A language given here always wins."
    • changedInput schema / properties / voice_id / description
      Previous value: -"A voice id from get_options; default: one that suits the goal."New value: +"A voice id from get_options; default: one that suits the goal, a native speaker of the language where we have one."
  5. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations, the description discloses critical behavior: no charge occurs, a draft project is created, free site analysis starts when a URL is provided, a quote with quote_id and credit details is returned, and quotes expire after 30 minutes. These details materially help the agent avoid unintended charges and sequence the approval correctly.

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?

The description is front-loaded with the most important constraint—step 1 of 2, nothing charged—and then covers the workflow and quote details. It is dense and somewhat long, but the length is largely justified by the tool's complexity and the need to prevent premature confirmation.

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 complex 21-parameter tool with no output schema, the description is quite complete: it describes the return payload, the approval workflow, quote expiration, and language resolution. Minor gaps such as explicitly restating that brief is required when no URL is given are covered by the schema rather than the description.

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 76% across 21 parameters, so the schema carries much of the burden, but the description adds meaningful semantics for goal selection, custom goal_description, pace defaults, and especially language precedence and fallback behavior. It does not explain every parameter in depth, but it adds value beyond the structured schema.

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?

The description states a specific verb and resource: it creates a draft project from a URL and/or brief and returns a quote. It clearly distinguishes this preparatory step from the follow-up approval action by naming confirm_operation and explaining that nothing is charged yet.

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?

It gives clear workflow guidance: show the returned quote to the user, and only call confirm_operation after approval of that exact amount; it also notes the 30-minute quote expiry. It does not explicitly compare this tool against sibling alternatives such as get_estimate, so it falls short of full when-versus-alternative guidance.

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.