Skip to main content
Glama

Plunder & Riffle Meme Engine

Whiteboard pitch video

create_whiteboard_pitch

Joe at the whiteboard: a narrated pitch/results page built from YOUR deck config (title, presenter {character, voiceRef}, business, scenes; chart scenes bignum/bars/versus draw the config's own numbers as SVG — the engine invents nothing). voice_id locks the narration voice for the call (overrides the config's voiceRef); scenes are auto-tagged chart/sketch/cta and the result reports the voice used + the tags. Returns pageUrl (preview); request_mp4 only after the human approves. 25 credits ($0.25; BYOK $0.01), refunded on failure.

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": {
      "config": "<config>"
    },
    "name": "create_whiteboard_pitch"
  }
}

Input Schema

NameRequiredDescriptionDefault
configYesThe full whiteboard-pitch deck config. Needs a presenter with a voiceRef and at least one chart scene with valid data.
voice_idNoNarration voice lock for this call — overrides config.presenter.voiceRef.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Beyond the lone destructiveHint=false annotation, the description discloses cost (25 credits, $0.25, BYOK $0.01), a failure refund policy, that the engine invents no numbers, auto-tagging of scenes, and that the result reports the voice and tags. That is substantial behavioral context for a mutation tool; only permission/auth requirements are unstated.

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 text is a single dense paragraph but front-loads the format and the key constraint (engine invents nothing), then layers cost and workflow. It is appropriately sized for a paid generative tool, though the run-on sentence structure makes it slightly harder to scan.

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?

For a nested-config tool with no output schema, the description covers the return (pageUrl preview), the reported voice/tags, cost, refunds, and the approval gate before MP4. It is nearly complete; minor gaps remain around error conditions or what the returned tags look like.

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: it enumerates the config's expected shape (title, presenter {character, voiceRef}, business, scenes) and the chart scene types (bignum/bars/versus) that draw the config's own numbers. The voice_id override is also restated in context of the call-level lock.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states what is produced: a narrated whiteboard pitch/results page built from the caller's deck config, with 'Joe at the whiteboard' establishing the distinctive format. It does not explicitly contrast itself with siblings like create_present or create_infomercial, so sibling differentiation is left to the format name alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

The description gives one clear sequencing rule — 'request_mp4 only after the human approves' — which names a sibling and a condition. However, it never says when to choose this tool over the other create_* pitch tools, so selection guidance is only implied by the format name.

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