Skip to main content
Glama

Plunder & Riffle Meme Engine

Render an approved preview as MP4

request_mp4

AFTER a human has approved a preview, start rendering an MP4 of that temp page (25 credits = $0.25; BYOK: $0.01 with your own Railway worker saved or when full BYOK — every required key saved at /vip-setup — else the full $0.25; refunded on failure). Takes 1–3 min. To skip polling pass callback_url and/or wait_seconds; otherwise poll get_job_status (kind mp4) with the jobId. Never render MP4s for unapproved previews.

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": {
      "pageUrl": "<pageUrl>"
    },
    "name": "request_mp4"
  }
}

Input Schema

NameRequiredDescriptionDefault
introNoOptional: "joe_call" opens the video with Joe calling on a phone to set up your video.
pageUrlYesThe approved pageUrl from generate_ad_creative.
outro_urlNoOptional: an https MP4 (up to 60 s) to play after this video instead of your account outro. null = no outro for this render.
orientationNoDefault vertical 9:16. Use "landscape" (16:9, no intro/outro clips) for a 16:9 page.
callback_urlNoOptional https webhook. Receives the signed done/failed result; the response carries the webhook secret once.
wait_secondsNoOptional, 0-100. Wait this long for the MP4 and return it in the same call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only supply destructiveHint=false, so the description carries the real burden and does: cost model (25 credits / $0.25, BYOK $0.01, refund on failure), expected duration (1–3 min), and the asynchronous job/webhook mechanics. This is exactly the context an agent needs before committing a paid, multi-minute render.

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 the approval precondition, then cost, then async behavior — a sensible priority order. The pricing parenthetical is dense and slightly hard to parse, but every clause conveys operational information rather than filler.

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?

No output schema exists, and the description compensates by explaining the jobId polling path and the signed webhook result, including that the secret is returned once. It stops short of describing what the immediate response contains when neither callback_url nor wait_seconds is supplied, a minor gap.

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 100%, so parameters are already documented; the description still adds the decision-level meaning — that callback_url and wait_seconds exist specifically to avoid polling, and that wait_seconds changes the call from async to synchronous. It does not restate the enum or per-param details, which is appropriate.

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 ("start rendering an MP4 of that temp page") plus the gating precondition (a human-approved preview). It is clearly distinguishable from the sibling that produces the preview (generate_ad_creative) and from the polling sibling (get_job_status).

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?

Explicitly says when to call (after human approval) and when not to ("Never render MP4s for unapproved previews"). It also names the alternative paths: pass callback_url and/or wait_seconds to skip polling, otherwise poll get_job_status with kind mp4.

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