Skip to main content
Glama

Generate a product ad from a page

autoshort_generate_product_ad
Idempotent

Create a product marketing video from a public product page by extracting product details and images, writing the ad, and generating editable scenes.

Instructions

Create a product marketing video from a public product page. AutoShort extracts product details and images, writes the ad, and creates editable scenes. Costs at least 40 credits; the exact quote is checked before the page is fetched. Rendering is asynchronous: poll autoshort_get_video every 20-30 seconds until status is COMPLETED or FAILED. If get_video returns blockedReason, stop polling and act on it (e.g. top up credits).

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": {
      "url": "<url>"
    },
    "name": "autoshort_generate_product_ad"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesPublic product page URL.
artStyleNoArt style returned by autoshort_list_niches.
durationNo
languageNoOutput language, or auto.
idempotencyKeyNoRetry-safe: a repeat with the same key returns the first answer (replayed: true) and creates nothing.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.3.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds material behavior beyond that: a minimum cost of 40 credits, a quote check that happens before the page fetch, and fully asynchronous rendering with a prescribed polling cadence. The blockedReason handling instruction is exactly the kind of failure-mode context annotations cannot express.

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

Conciseness5/5

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

Four sentences, each doing distinct work: what it makes, what it costs and when the check fires, the async polling contract, and the failure branch. Front-loaded with purpose and cost, no filler or restatement of the name.

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?

There is no output schema, so the description carries the return contract, and it does explain status values and blockedReason. The one gap is what the create call itself returns (the job/video identifier the agent must pass to autoshort_get_video), which the agent must infer or discover at runtime. Otherwise complete for a 5-parameter, cost-bearing, async generation tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 80%, so the schema already carries most parameter meaning (registry-validated artStyle from autoshort_list_niches, duration bounds, language auto, idempotency replay semantics). The description adds nothing parameter-specific beyond the implicit constraint that the URL must be a public product page. Baseline 3 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?

Opens with a specific verb and resource: "Create a product marketing video from a public product page." The source (a public product page) plus the follow-up sentence on extraction, copywriting, and editable scenes distinguishes it from the sibling generators (chat, image-to-video, motion clip) without the agent needing to open their schemas.

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

Usage Guidelines4/5

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

Gives clear operational guidance: poll autoshort_get_video every 20-30 seconds until COMPLETED or FAILED, and stop on blockedReason rather than continuing to poll. It stops short of explicitly stating when to prefer a different generator (e.g. for non-product-page sources), but the source constraint is implicit in the opening sentence.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.