Skip to main content
Glama

Render a draft

render_draft
Idempotent

Render an approved draft into the video. THIS IS THE ONLY STEP THAT COSTS CREDITS: the price is quote.credits from get_draft / draft_video, charged once after the render succeeds (a failed attempt costs nothing; StoryShort may retry a failed render automatically, up to 3 times, and the same video is never charged twice — cancel_video stops the retries). Call it first without confirmCredits to get QUOTE_REQUIRED and the price, show the user, then call again with confirmCredits set to that exact number. A wrong number is refused (PRICE_CHANGED); a short balance is refused up front (INSUFFICIENT_CREDITS). A new account with no credits that has not had its free first video gets it here instead of an error: watermarked, labelled AI-generated, up to 30 seconds, standard voice, one per account, subject to the day's availability. That first video needs no confirmCredits; the answer carries its video id. Calling it again on a draft that is already rendering starts nothing new. Poll get_video until COMPLETED or FAILED. Requires the "video:create" scope.

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": {
      "draftId": "<draftId>"
    },
    "name": "render_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
draftIdYes
confirmCreditsNoThe render price in credits the user approved (quote.credits).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare non-read-only, idempotent, non-destructive, open-world, and the description goes well beyond them: credit charging semantics (charged once after success, failures free, up to 3 automatic retries, never double-charged), refusal codes (QUOTE_REQUIRED, PRICE_CHANGED, INSUFFICIENT_CREDITS), the free-first-video constraints, and the required 'video:create' scope. The 'starts nothing new' statement is consistent with idempotentHint. This is rich disclosure, but it is all packed into one dense paragraph rather than separated from the annotation-covered basics.

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

Conciseness3/5

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

The cost warning is correctly front-loaded and every clause carries real information, but the definition is a single very long paragraph of stacked parentheticals (retry count, free-video constraints, error codes) with no structural breaks. It is dense rather than wasteful, yet the free-first-video detail could be tightened or split to keep the primary call flow scannable.

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 no output schema, the description carries the return burden and does so for the key cases: QUOTE_REQUIRED response, the video id returned for a free first video, and the instruction to poll get_video until COMPLETED or FAILED. For a credit-charging, retry-prone render tool this is close to complete; only the normal paid-success response shape is left implicit.

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 50% (confirmCredits documented, draftId bare). The description compensates strongly for confirmCredits, explaining where the number comes from (quote.credits), that it must match exactly, and how mismatches are refused. draftId is left implicit, which is a minor residual gap for an otherwise well-explained parameter.

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?

Opens with a specific verb and resource ('Render an approved draft into the video') and immediately marks the boundary versus siblings: quoting happens in get_draft/draft_video, polling in get_video, retry cancellation in cancel_video. An agent can distinguish this from quote_video or create_video without opening any 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 an explicit two-call sequence (first without confirmCredits to obtain QUOTE_REQUIRED and the price, then with the exact approved number), names the alternative tools for each adjacent step, and specifies the exception path for a new account's free first video. When-to-use, when-not-to-confirm, and what to do after the call are all stated.

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