Skip to main content
Glama

Plunder & Riffle Meme Engine

Content from one offer link

create_funnel

/funnel: ONE offer link becomes voiced content whose CTA is that link: captions (+ an iMessage thread; voiced typography page, no memes), memes (timed-caption voiced page with memes, an iMessage thread, + a picture or iMessage meme) or a stick-figure story; format bestof builds a silent day of content (2 memes, an iMessage, a slideshow, a ranked list) AND publishes one share page bundling everything (dayPack.shareUrl); format share rebuilds that page. Reads the page (never invents; unreadable = status needs-description, then call with funnel_id + description). Omit format to analyze first; switch with funnel_id + format, no new link. 10 credits to read; captions 25, memes 35, stickfigures 25, bestof 60 (BYOK $0.01/call); refunded on failure. Poll get_job_status (kind funnel, jobId = funnelId). Previews only: show offer.url under them; no posting or MP4 without the human's OK. For an MP4, pass mp4PageUrl (the creative — a voiced video, the show, a meme) to request_mp4, never dayPack.shareUrl, which is the carousel bundle.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_funnel"
  }
}

Input Schema

NameRequiredDescriptionDefault
ctaNoButton label under the preview. Default: from the product name.
urlNoThe offer link, kept exactly (referral params untouched). Not needed with funnel_id.
kindNomemes only: meme | imessage (default: alternates).
toneNo
angleNo
formatNocaptions | memes | stickfigures | all | bestof
scriptNoYour own words, spoken as is.
contextNo
rebuildNoWith funnel_id: the same funnel again, made fresh.
audienceNo
languageNo
platformNo
funnel_idNoEarlier funnelId: switch format, regenerate, describe or rebuild without the link.
objectionNo
variationNosame = regenerate, next = new angle (default same).
descriptionNoWhat the offer is and who it's for, when the page can't be read.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

The single annotation only declares destructiveHint=false, so the description carries the real behavioral load — and it does: credit prices per format (10/25/35/25/60, BYOK $0.01), refund on failure, the needs-description fallback when a page can't be read, and the hard gate that previews must not be posted or exported without human approval. That is substantially more than the annotations convey.

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 purpose is front-loaded, but the body is a single dense paragraph of slash-separated clauses and stacked parentheticals that forces re-reading. The important MP4-vs-shareUrl warning, arguably the most useful sentence, is buried at the end.

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, yet the description still surfaces the key return handle (dayPack.shareUrl) and the jobId/funnelId correlation needed to poll results, plus the asynchronous completion model. Given 16 parameters and multiple modes, this is close to complete, though the non-mentioned stylistic parameters remain opaque.

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?

With 16 parameters and 56% schema coverage, the description adds real meaning for the highest-risk ones: url vs funnel_id ('no new link'), format switching, the needs-description path for 'description', and rebuild/variation semantics. It leaves tone, angle, script, context, audience, language, platform and objection entirely to the schema, so coverage is partial but the gaps are mostly low-risk stylistic fields.

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 opening '/funnel: ONE offer link becomes voiced content whose CTA is that link' names the verb (create), the input (one offer link), and the output (voiced content with that CTA), then enumerates the concrete formats (captions, memes, stickfigures, bestof, share). An agent can distinguish this from get_job_status or request_mp4 without opening a 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?

It explicitly states when to omit format ('analyze first'), how to switch modes ('funnel_id + format, no new link'), and how to proceed after a call ('Poll get_job_status (kind funnel, jobId = funnelId)'). It also names a concrete alternative and its exclusion: use request_mp4 with mp4PageUrl, 'never dayPack.shareUrl'.

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