Skip to main content
Glama

Prepare a variant (quote)

request_variant

Step 1 of 2: nothing is charged. Prices a variant of a ready video: translate (languages), reformat (aspect ratios, recomposed not cropped), recreate (new takes with the same settings, or another pace, the project's code screens and Brand Kit included, priced like the web app's Recreate) or export_4k. Returns a quote_id for confirm_operation.

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": {
      "video_id": "<video_id>",
      "kind": "<kind>"
    },
    "name": "request_variant"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
paceNorecreate: the new takes' pace, calm (Calm), normal (Balanced) or fast (Punchy), e.g. a calmer take of a film that feels too fast. Default: the pace the project's films were made at. Same price.
countNorecreate: how many new takes.
aspectsNoreformat: target aspect ratios.
video_idYes
voice_idNotranslate: a voice from get_options (default: the video's voice when it is a native speaker of the language, else a native voice of the language).
languagesNotranslate: target language codes (get_options).
visibilityNoDefault: the same as the source video (recreate: the project's choice if it made one; a project made from code starts private).
review_storyboardNorecreate: pause after each new take's storyboard for approve_storyboard. Default: the project's create_project review_storyboard, else false (confirm_operation is the only approval; a take still pauses if its price would exceed the quote).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / pace / description
      Previous value: -"recreate: the new takes' pace, calm (Calm), normal (Balanced) or fast (Punchy), e.g. a calmer take of a film that feels too fast. Default: the project's (its pick, else its goal's). Same price."New value: +"recreate: the new takes' pace, calm (Calm), normal (Balanced) or fast (Punchy), e.g. a calmer take of a film that feels too fast. Default: the pace the project's films were made at. Same price."
    • addedInput schema / properties / review_storyboard
      Added value: +{
      +  "description": "recreate: pause after each new take's storyboard for approve_storyboard. Default: the project's create_project review_storyboard, else false (confirm_operation is the only approval; a take still pauses if its price would exceed the quote).",
      +  "type": "boolean"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / pace
      Added value: +{
      +  "description": "recreate: the new takes' pace, calm (Calm), normal (Balanced) or fast (Punchy), e.g. a calmer take of a film that feels too fast. Default: the project's (its pick, else its goal's). Same price.",
      +  "enum": [
      +    "calm",
      +    "normal",
      +    "fast"
      +  ],
      +  "type": "string"
      +}
  3. Changed1 schema field changed
    • changedInput schema / properties / voice_id / description
      Previous value: -"translate: a voice from get_options (default: the video's voice)."New value: +"translate: a voice from get_options (default: the video's voice when it is a native speaker of the language, else a native voice of the language)."
  4. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses that this call charges nothing, that a quote_id is produced and must be consumed by confirm_operation, and that recreate pricing matches the web app's Recreate and is unchanged by pace. For a non-readOnly, non-idempotent tool, that is exactly the safety context an agent needs before invoking step 1 of a two-step purchase flow.

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 most important fact, 'nothing is charged', is front-loaded in the opening clause, and the return contract closes the sentence. The middle is a dense run-on enumerating four kinds with nested parentheticals, which is informative but harder to scan than it needs to be.

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 nine parameters, 78% schema coverage and no output schema, the description carries the return-value burden and does so by naming quote_id and its consumer. It omits what else the quote contains (price, expiry, scope) and any error or retry behavior, which leaves a small gap for a priced two-step operation.

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 78%, so the schema already labels kind, languages, aspects, pace and count. The description adds genuine meaning the schema lacks: reformat is 'recomposed not cropped', and the parenthetical grouping tells the agent which parameter families belong to which kind (translate→languages, reformat→aspect ratios, recreate→new takes/pace).

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 ('Prices a variant of a ready video') and enumerates the four supported kinds (translate, reformat, recreate, export_4k), which maps directly onto the kind enum. It also distinguishes itself from the downstream sibling by naming confirm_operation as step 2, so an agent can place it in the workflow without opening the schema.

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?

'Step 1 of 2: nothing is charged' plus 'Returns a quote_id for confirm_operation' gives an explicit precondition and the follow-up tool to call, which is strong routing guidance. It does not, however, differentiate from the other cost/pricing sibling get_estimate, nor state what to do if the underlying video is not ready.

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.