Skip to main content
Glama
Sign In

Shipfound

by co.shipfound
OverviewDiscussionsAdmin

Make the AI presenter video

ugc_start

Make a priced AI presenter video from ugc_plan, after the founder said yes to its price: holds the whole price from the balance and starts the images (the presenter's portrait when new, then the over-the-shoulder frame). With frames ok, after you looked at both images (ugc_status), makes the clip; with frames stop, ends it, charged for the images only. Charged at Higgsfield's cost plus the margin for what is made; a request Higgsfield fails or flags is not charged. $6.62 at most.

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": {
      "job": "<job>"
    },
    "name": "ugc_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobYesThe job from ugc_plan
framesNoAfter the images: ok makes the clip, stop ends it

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior5/5

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

Annotations only cover read/write and open-world hints; the description adds genuinely new behavior - a full-price hold against the balance, cost-plus-margin billing, no charge for failed or flagged requests, and a stated maximum of $6.62. This is exactly the financial and side-effect context an agent cannot infer from structured fields.

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?

Everything is packed into one long, parenthesis-heavy run-on that mixes purpose, billing, and state-machine logic. The purpose is front-loaded and the content mostly earns its place, but the tangling makes it slower to parse than it needs to be.

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 paid, stateful mutation tool with no output schema, the description covers cost, cap, failure policy, and the two-mode lifecycle well. The remaining gap is what the call returns (job identifier, immediate status, or nothing until ugc_status is polled), which an agent would want to know.

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 coverage is 100% and both parameter descriptions already explain 'job from ugc_plan' and 'ok makes the clip, stop ends it', so the schema does the heavy lifting. The description adds only sequencing context (that 'frames' applies after the images are generated and inspected), which is mild added meaning.

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 opens with a specific verb and resource ('Make a priced AI presenter video from ugc_plan') and names the sibling it depends on, so an agent can separate it from ugc_plan and ugc_status. The core purpose is clear, though the first sentence then wanders into balance-hold and image-generation detail that blurs the headline action.

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?

It states explicit preconditions: only after the founder accepts the price, and with frames='ok' only after inspecting both images via ugc_status; frames='stop' terminates the job. That is close to a full when-to-use/when-not map, but it never clarifies what omitting 'frames' on the first invocation does, leaving the entry path implied.

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

All Shipfound toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources