Shootika

Request scene

request_scene

Idempotent

Asks for a scene (a model in a style and pose) to shoot with. A library model on a preset style is free. A custom model's scene, or a scene on the store's own setting (a ref: style), uses 1 frame from the store's plan (an extra frame if the plan bills them and this connection may), refunded if it fails, so ask the person before requesting one they did not ask for. Safe to repeat: a scene the store already has comes back as it is, with no new charge. A new scene takes a little while to prepare; check list_scenes and start the shoot once its status is ready.

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_id": "<model_id>",
      "style": "<style>",
      "pose": "<pose>"
    },
    "name": "request_scene"
  }
}

Input Schema

Name	Required	Description
`pose`	Yes	One of the model's poses from list_models, such as Front.
`style`	Yes	A style key from list_styles.
`model_id`	Yes	The model id from list_models.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 25, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Adds substantial context beyond the annotations: exact cost (1 frame, extra if the plan bills them), refund on failure, idempotent no-charge repeat behavior, and asynchronous preparation latency. These directly explain what the idempotentHint and non-readOnly hints mean in practice.

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 definition, then cost, then repeat-safety, then async behavior — no wasted sentences. The nested parentheticals ('an extra frame if the plan bills them and this connection may') are dense enough to slow parsing slightly.

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?

For a 3-required-param creation tool with no output schema, it covers the missing pieces an agent needs: billing, confirmation etiquette, idempotency, latency, and the next step after creation. Nothing material is left unexplained.

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 baseline is 3; the description still adds meaning by tying 'style' to the store's own setting (a ref: style) that triggers billing and by framing model/style/pose as the scene composition. It does not add syntax details beyond the schema's list_models/list_styles pointers.

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?

States a specific verb and resource and defines the resource inline ('a scene (a model in a style and pose)'), so an agent knows exactly what gets created. The follow-on routing to list_scenes and start_shoot separates it from the listing and shooting 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?

Explains the two cases (free library model on preset style vs. paid custom/ref: style scene) and instructs the agent to confirm with the person before spending frames they did not request. It gives the post-call workflow (poll list_scenes, then start_shoot) but no explicit 'when not to use this' beyond the cost caveat.

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

All Shootika 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?