Squall Studio

Generate background plate

generate_shot_background_image

Generate an empty background plate for one short shot. Both reference inputs steer what the plate itself looks like — layout, prop identity, materials and lighting — and are unrelated to upload_shot_continuity_reference, which guides clip generation instead. Use reference_image_asset_ids for images already in this project (find them with get_asset_library) and reference_images_base64 to send bytes you produced locally, for example a frame lifted from an earlier scene so a prop matches what is already on screen. Uploaded bytes are used for this one generation and are not kept as project assets. The location's own reference images are always included on top of both. Spends credits. Returns a job id — poll it with get_job.

Input Schema

TableJSON Schema

Name	Required	Description
`shot_id`	Yes	Shot id.
`idempotency_key`	Yes	Stable key identifying this generation request. Reuse the SAME key when retrying the same request — the original job is returned and no second charge is made. Use a NEW key when you deliberately want another generation.
`short_shot_number`	Yes	Short shot number within the shot.
`reference_images_base64`	No	Images to send as bytes. PNG, JPEG and WebP only; the bytes are sniffed, so the filename extension alone will not get a non-image through. Keep them small — a 720x1280 JPEG is roughly 40-130KB of base64.
`reference_image_asset_ids`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 8, 2026

addedInput schema / properties / reference_images_base64

Added value: +{
+  "description": "Images to send as bytes. PNG, JPEG and WebP only; the bytes are sniffed, so the filename extension alone will not get a non-image through. Keep them small — a 720x1280 JPEG is roughly 40-130KB of base64.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "filename": {
+        "description": "File name to send it under, e.g. scene-1-radio-prop.jpg.",
+        "maxLength": 255,
+        "minLength": 1,
+        "type": "string"
+      },
+      "image_base64": {
+        "description": "The image bytes, base64-encoded. No data: URI prefix.",
+        "maxLength": 34000000,
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "filename",
+      "image_base64"
+    ],
+    "type": "object"
+  },
+  "maxItems": 3,
+  "type": "array"
+}

First observedSep 7, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=false. The description goes beyond by stating that uploaded bytes are not kept as project assets, that location references are always included, that it spends credits, and that it returns a job id. This adds valuable context about persistence, cost, and async behavior that the annotations do not convey.

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?

The description is dense but every sentence carries essential guidance. It front-loads the core purpose and then spaces out input selection, side effects, and return handling. Slightly long, but appropriate for the tool's complexity; no filler.

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 tool with 5 parameters, async job result, costs, and side effects, the description covers all necessary aspects: what it generates, how to feed references, what gets persisted, how to retrieve the result, and cost implications. No output schema exists, but the description explicitly states the return type (job id). The guidance is sufficient for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Though schema coverage is 80%, the description clarifies the semantic difference between the two reference parameters (asset IDs vs base64 bytes) and explains idempotency behavior (reuse key to avoid double charge). This provides meaning far beyond the raw schema definitions, especially for reference_image_asset_ids which lacks a schema description.

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 states a specific verb-resource pair ('Generate an empty background plate for one short shot') and distinguishes it from sibling tools by noting that the reference inputs steer plate appearance, explicitly unrelated to upload_shot_continuity_reference. The purpose is unambiguous and clearly delimited from the other generation tools.

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?

Explicitly differentiates when to use reference_image_asset_ids vs reference_images_base64, explains that location references are always included, mentions it costs credits and returns a job id to poll. It also draws a contrast with upload_shot_continuity_reference, giving clear selection criteria.

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

All Squall Studio 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?