Squall Studio

Upload continuity reference

upload_shot_continuity_reference

Attach an image you produced locally to a shot as a continuity reference. A continuity reference is fed into this shot's next clip generation as a layout, prop, wardrobe and screen-direction guide — it is NOT used as the shot's opening frame or exact composition. Attaching one changes nothing until the clip is generated again. Send the image as base64 — keep it small (a 720x1280 JPEG is roughly 40-130KB of base64). PNG, JPEG and WebP only; the bytes are sniffed, so the filename extension alone will not get a non-image through. If the image is already an asset in this project, use attach_shot_continuity_reference instead and send no bytes.

Input Schema

TableJSON Schema

Name	Required	Description
`shot_id`	Yes	Shot id (episode_shots row) to attach the reference to.
`filename`	Yes	File name to store it under, e.g. scene-1-last-frame.jpg.
`guidance`	No	How the video model should use this reference, e.g. which positions or props to match and what to ignore. Saved on the reference and sent with every later generation of the shot.
`image_base64`	Yes	The image bytes, base64-encoded. No data: URI prefix.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 14, 2026

addedInput schema / properties / guidance

Added value: +{
+  "description": "How the video model should use this reference, e.g. which positions or props to match and what to ignore. Saved on the reference and sent with every later generation of the shot.",
+  "maxLength": 1000,
+  "type": "string"
+}

AddedSep 7, 2026

TDQS

A4.9/5.0

Behavior5/5

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

The annotations only say readOnlyHint=false and destructiveHint=false, so the description carries the behavioral burden and does so thoroughly. It explains the reference is fed into later clip generation as a layout/prop/wardrobe/screen-direction guide, that attaching changes nothing until the clip is generated again, and that bytes are sniffed so a fake filename will not pass a non-image through.

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?

The description is four sentences with no filler; every sentence contributes either a core definition, a behavioral caveat, a validation constraint, or sibling routing. It front-loads the primary purpose and places the most important 'not' semantics early.

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 4-parameter mutation tool with no output schema, this description covers what the tool does, what happens after attachment, what validation applies, and which sibling to use instead. There is no obvious missing context an agent would need to invoke it correctly.

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 meaningful practical semantics: suggested base64 size, accepted image formats, the no-data-URI rule, and the fact that guidance is saved and sent with every later generation. It does not deeply enrich shot_id, but the extra parameter guidance is substantial enough to raise the score.

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 opens with a specific verb and resource: 'Attach an image you produced locally to a shot as a continuity reference.' It also draws a sharp boundary by stating what it is NOT ('NOT used as the shot's opening frame or exact composition') and explicitly names the sibling attach_shot_continuity_reference, so an agent can distinguish them immediately.

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?

The description gives explicit routing guidance: 'If the image is already an asset in this project, use attach_shot_continuity_reference instead and send no bytes.' It also implies this tool is for locally produced images that are not yet project assets, which is exactly the when-to-use vs. alternative decision an agent needs.

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?