switch

Upload Reference

upload_reference_asset

Upload an image, video, or audio reference into Switch cloud and get an opaque asset_id (never a raw storage URL) to pass in reference fields. Pass kind=image|video|audio. Returns reference_image_urls / reference_video_urls / reference_audio_urls for generate_image and generate_video. Image references are also added to your active Studio reference strip (the same one your desktop uses) unless activate=false; the strip is PHOTOS ONLY — video and audio never touch it. PREFERRED for real files: call with presign=true to get an upload_url, PUT the bytes straight to it (no base64 through the model), then call again with confirm_path to verify and add it — works for image, video, and audio. base64/url is only for tiny inline files.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	No	Public https URL to fetch server-side.
`kind`	Yes	Reference type to upload.
`mime`	No	MIME for base64. Images: jpg/png/webp/gif. Videos: mp4/mov. Audio: mp3/wav/m4a/aac.
`base64`	No	Base64 bytes (optionally a data: URL). Best for small files; large video should use presign.
`presign`	No	Return an upload_url to PUT the file bytes directly to (no base64). Video always; image/audio when enabled.
`activate`	No	Image only: add to the active Studio reference strip. Default true. The strip is photos only — video and audio never touch it regardless of this flag.
`filename`	No	Optional source filename for extension/display.
`frame_type`	No	Image strip label: ref (default), face, body, clothes, scenery, product, typography. Use "face" for a person's face/likeness — face uploads are stored as untouched originals in the private reference bucket and their returned asset_id is the ONLY handle face-capable generation accepts (KYC-verified accounts only).
`confirm_path`	No	The storage_path from a presign call, after you PUT the file — verifies the object, records it, and adds it to your strip.

TDQS

A4.5/5.0

Behavior4/5

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

Annotations only indicate readOnlyHint=false and idempotentHint=false, which is minimal. The description adds substantial behavioral context: the presign two-step flow, the fact that video/audio never touch the strip, the face upload special handling, and the opaque asset_id guarantee. It doesn't contradict annotations, and it goes beyond what annotations provide.

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 well-structured, front-loading the core purpose and then explaining the preferred workflow. It's longer than ideal but every sentence adds meaningful information about usage, constraints, or behavior. The structure flows logically from purpose to workflow to edge cases.

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?

Given the tool's complexity (9 parameters, multiple workflows, special cases), the description covers the key aspects: the presign flow, the strip behavior, the face upload special case, and the return values. It doesn't have an output schema, so it explains what the tool returns (asset_id, reference URLs). Minor gaps like error handling or rate limits are not critical for basic usage.

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 description coverage is 100%, so the schema already documents all parameters. The description adds value by explaining the presign/confirm_path workflow, the activate flag's strip behavior, and the frame_type 'face' special handling. It doesn't repeat schema details but adds workflow context that helps the agent use parameters correctly.

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 clearly states the tool uploads image, video, or audio references into Switch cloud and returns an opaque asset_id. It distinguishes itself from siblings like upload_media and upload_editor_media by specifying the reference context and the returned asset_id usage in reference fields.

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 provides explicit guidance on when to use this tool vs alternatives: it mentions the preferred presign flow for real files, notes that base64/url is only for tiny inline files, and clarifies that video/audio never touch the Studio strip. It also explains the activate flag behavior for images.

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

All switch tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.5/5.0

Disambiguation2/5

Several tools occupy nearly identical semantic ground: apply_iphone_realism and apply_ugc both describe casual phone-shot looks, upload_media and upload_reference_asset both accept uploads, and analyze_video overlaps heavily with analyze_video_report. The many apply_* style tools are essentially one tool parameterized by style, so agents can easily select the wrong one.

Naming Consistency4/5

Most tools follow a clear verb_noun snake_case pattern such as generate_image, list_my_videos, get_editor_run, and upscale_video. A few outliers like voice, talking_avatar_video, and video_to_prompt do not use the same verb-first convention, but they are still readable and do not create significant confusion.

Tool Count1/5

At 55 tools, the surface is far beyond what is appropriate for an MCP server; many of these be collapsed or parameterized, especially the 10 apply_* style wrappers and several overlapping upload/status helpers. Even for a broad media platform, this scale forces a huge context window and makes selecting the right tool impractical.

Completeness2/5

The surface covers generation, media display, video analysis, and Editor workflows well, but there are obvious gaps in library lifecycle management: move_asset and create_folder are referenced in tool descriptions without being exposed, and there is no clean way to delete or reorganize media assets. Agents following the descriptions will try to call tools that do not exist.

Resources

Need Help?