Shootika

Start shoot

start_shoot

Destructive

Starts a shoot: one new frame of the product in the scene's style, on the scene's model, or the product alone for a placement scene (kind lifestyle). Each call uses one frame (two on a ghost mannequin) from the store's plan, so ask the person before starting shoots they did not ask for, and pass a request_id so a retry does not shoot twice. Pass notes to say how the product is worn or presented; notes never change the model or the scene. Returns at once with the frame queued; call get_shoot with its id to wait for the result.

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": {
      "product_id": "<product_id>",
      "source_image_id": "<source_image_id>",
      "scene_id": "<scene_id>"
    },
    "name": "start_shoot"
  }
}

Input Schema

Name	Required	Description
`notes`	No	A short styling note: how to wear the product on a model, or how to present it in a product shot.
`scene_id`	Yes	A ready scene id from list_scenes, of a kind the product's shoot_routes allow.
`product_id`	Yes	The product id from list_products.
`request_id`	No	Any unique string for this shoot. Repeating a call with the same request_id within 24 hours returns the first result instead of starting and charging a second shoot.
`regenerate_of`	No	A frame id, to shoot that frame again.
`source_image_id`	Yes	The id of one of the product's photos (get_product).
`garment_photo_type`	No	flat-lay (the default) when the photo shows the product alone, model when someone is wearing it. Ignored for a placement scene.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 28, 2026

changedInput schema / properties / garment_photo_type / description

Previous value: -"flat-lay (the default) when the photo shows the garment alone, model when someone is wearing it."New value: +"flat-lay (the default) when the photo shows the product alone, model when someone is wearing it. Ignored for a placement scene."

changedInput schema / properties / notes / description

Previous value: -"A styling note for the model: how to wear the product (\"sleeves pushed up\", \"tucked in\"). It cannot change the model, the scene or the pose; ask for a different scene for that."New value: +"A short styling note: how to wear the product on a model, or how to present it in a product shot."

changedInput schema / properties / scene_id / description

Previous value: -"A ready scene id from list_scenes."New value: +"A ready scene id from list_scenes, of a kind the product's shoot_routes allow."

Changed1 schema field changedOct 26, 2026

addedInput schema / properties / notes

Added value: +{
+  "description": "A styling note for the model: how to wear the product (\"sleeves pushed up\", \"tucked in\"). It cannot change the model, the scene or the pose; ask for a different scene for that.",
+  "maxLength": 240,
+  "type": "string"
+}

First observedOct 25, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only mark this as destructive/non-idempotent; the description adds the crucial context that each call consumes one frame (two on a ghost mannequin) from the store's plan, that request_id dedupes within 24 hours, and that the call is asynchronous—returning immediately with a queued frame that must be awaited via get_shoot. That is exactly the cost and lifecycle information an agent needs before invoking a chargeable write.

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-loaded with what the tool produces, then cost, then safety, then return behavior—good ordering with no filler. Sentences are long and clause-heavy, but each carries a distinct, non-redundant fact.

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 an asynchronous, credit-consuming generation tool with no output schema, the description covers scope, cost, idempotency, styling limits, and the required follow-up call. Nothing an agent needs to invoke it correctly is missing.

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 baseline is 3, but the description adds semantics beyond the schema: notes constrain styling only and 'never change the model or the scene,' and request_id is framed as the safeguard against duplicate charges. It does not cover regenerate_of or garment_photo_type, which the schema handles on its own.

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 ('Starts a shoot') and immediately defines what a shoot produces: one new frame of the product in the scene's style, on the scene's model, or a product-only shot for placement scenes. It is clearly distinguishable from siblings like get_shoot, add_product_image, and request_scene.

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 explicit operating guidance: ask the person before starting shoots they did not request, pass a request_id so retries don't double-charge, and use notes only for styling. It stops short of saying when to prefer regenerate_of over a fresh shoot, which is the one routing decision left implicit.

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?