Skip to main content
Glama
Sign In

Shillbot — AI Agent Crypto Bounties, Lean 4 Proofs & x402 Video

by io.github.corsur
OverviewDiscussionsAdmin

generate_video

Destructive

[SPEND: 5 USDC] Generate a short-form video from a prompt or URL (x402 payment, Base/Ethereum/Polygon/Solana). First call returns {status: "payment_required", payment_details} — pay that amount to that address, then re-call with tx_signature to start generation. Poll the returned session_id with check_video_status. Tip: submit the video to a Shillbot task via shillbot_submit_work to earn back more than the spend.

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": {
      "prompt": "<prompt>"
    },
    "name": "generate_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoOptional URL to use as context for video generation.
promptYesA text prompt describing the video to generate (max 1000 chars).
tx_signatureNoSolana/EVM transaction signature proving USDC payment. Omit on first call to get payment instructions.

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 declare a non-read-only, destructive, non-idempotent, open-world operation, and the description supplies the concrete facts behind those hints: a 5 USDC spend, the supported chains (Base/Ethereum/Polygon/Solana), and the exact first-call response shape with the payment handshake. It also makes clear generation is asynchronous and resumes only after a tx_signature is supplied, which explains the non-idempotent flag in practical terms.

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 most decision-relevant fact (the spend) and then sequences the call flow in order. It is dense but every clause carries operational information; the trailing Shillbot tip is a mild cross-sell but still actionable.

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?

There is no output schema, and the description compensates by specifying the first-call return payload and the session_id used for polling. For a paid, asynchronous, multi-step tool, an agent has everything needed to call it correctly and to recover from the payment-required state.

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 field definitions already exist, but the description adds workflow meaning the schema lacks: tx_signature is a payment proof that must be omitted on the first call, and the prompt/URL choice is framed as prompt-or-URL sourcing. It stops short of describing prompt format constraints beyond what the schema states.

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+resource ("Generate a short-form video") and the two accepted inputs (prompt or URL), plus an up-front cost marker. This clearly separates it from check_video_status, which only polls an existing job.

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 two-step procedure: first call returns payment_required, pay, then re-call with tx_signature. It also names the follow-up tool (check_video_status) for polling and points at shillbot_submit_work as an optional downstream action, so the agent knows both when to call and what to do next.

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

All Shillbot — AI Agent Crypto Bounties, Lean 4 Proofs & x402 Video toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources