Skip to main content
Glama

Plunder & Riffle Meme Engine

Another post from a finished job

create_followup

The follow-up buttons over MCP: rebuild what a finished video ALREADY said as another post — same subject, same points, nothing new invented. Pass ONE source: job_id (a done sitdown / phone / best-of job), source_id (the id a create_before_pitch returned), or context (the text to build on). format is the output: meme, slideshow, hottake (10 credits, $0.10; BYOK: $0.01) or imessage (20 credits, $0.20). The email follow-up is the note on continue_two_step (followUpGate), not this page. Returns the new pageUrl directly (no polling); show it, and only after the human approves call request_mp4 with it. Refunded on failure. Nothing is sent.

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": {
      "format": "<format>"
    },
    "name": "create_followup"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoWith context: what the material came from (default note).
titleNoWith context: what it is, e.g. "Pitch for Maria".
formatYesmeme = one image; imessage = a narrated thread.
job_idNoA FINISHED sitdown or phone jobId — its own script becomes the material.
contextNoMaterial to build from when there is no id: the script, the pitch text or the key points (≤4000 chars).
languageNoWith context: output language. A job/pitch keeps its own.
source_idNoThe `id` from create_before_pitch — the pitch is remembered for 2h.
instructionNoOptional one-line direction for THIS piece (e.g. "make it about the interview, not the layoff"), ≤300 chars.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare destructiveHint=false; the description carries everything else the agent needs: per-format credit and dollar costs, BYOK pricing, refund on failure, no polling required, an explicit human-approval gate before request_mp4, and the assurance that nothing is sent. These are exactly the behavioral facts a caller must know before spending credits.

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-loads the core purpose, then source selection, then format/pricing, then post-call flow — a sensible ordering with no filler sentences. It is dense and somewhat parenthetical-heavy (credit prices inline), which slightly slows scanning but every clause carries operational information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 8 parameters and no output schema, the description still covers the essentials: the one-of source rule, the format enum with costs, and the return value ('returns the new pageUrl directly, no polling'). Nothing an agent needs in order to invoke it correctly and handle the result is missing.

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 the baseline is 3, but the description adds real meaning the schema cannot express: job_id, source_id, and context are mutually exclusive with 'pass ONE,' and job_id is narrowed to finished sitdown/phone/best-of jobs. The format pricing also adds decision-relevant context. It stops short of 5 because the per-parameter detail largely mirrors the schema's own descriptions.

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 precise verb+resource: rebuild what a finished video already said as another post, explicitly constrained to 'same subject, same points, nothing new invented.' It also carves out what it is NOT (the email follow-up lives on continue_two_step, not here), so an agent can separate it from adjacent tools 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit one-of rule ('Pass ONE source') naming all three alternatives and their preconditions (job must be done, source_id from create_before_pitch, or raw context text). It also prescribes the downstream flow: show the returned pageUrl, wait for human approval, then call request_mp4. That is when-to-use, when-not-to-use, and the follow-on action in one pass.

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