API Stock

Create generation

create_generation

Start a generation. Charges the user's balance and returns a taskId at once; the result arrives later — poll get_task. A failed generation is refunded.

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": {
      "model": "<model>",
      "input": "<input>"
    },
    "name": "create_generation"
  }
}

Input Schema

Name	Required	Description
`input`	Yes	Model parameters, exactly as get_model lists them (camelCase). Media inputs are public URLs.
`model`	Yes	Model id from list_models, for example `veo3.1-fast`.
`webhook`	No	HTTPS URL to call when the generation completes.
`maxCostUsd`	No	Refuse the request if it would cost more than this.
`idempotencyKey`	No	Repeat a call with the same key and the same request to get the same task instead of a second charge.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Beyond the annotations, it discloses the two facts an agent most needs: money is charged immediately, and failed generations are refunded. It also makes the async contract explicit. It does not describe webhook delivery timing or how the charge interacts with maxCostUsd refusals, so it is strong but not exhaustive.

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?

Three short sentences, front-loaded with the primary action, then the async caveat, then the refund guarantee. Every clause carries information and none repeats the name or title.

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 billable, asynchronous mutation with a free-form nested input object and no output schema, the description covers the crucial lifecycle and cost semantics. Remaining gaps, such as where the finished artifact is listed and webhook delivery guarantees, are minor since the schema covers those parameters.

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 100%, so model, input, webhook, maxCostUsd and idempotencyKey are already documented in the schema. The description adds no parameter-level meaning beyond that, which lands at the baseline for fully covered schemas.

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?

The description pairs a specific verb with its resource ("Start a generation") and immediately defines the tool's contract: it charges balance and returns a taskId synchronously. Naming get_task as the follow-up distinguishes it from list_generations and the read-only siblings.

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 gives clear post-call guidance ("the result arrives later — poll get_task"), which is exactly what an agent needs after invoking. It stops short of saying when NOT to call it or when to pre-check with estimate_cost / maxCostUsd, so explicit alternative routing is absent.

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

All API Stock tools Inspect

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

Need Help?