Upload a local file from the MCP server's filesystem to a presigned upload_url returned by the upload-URL endpoint. Use this for local CLI testing when the server can read the file path; remote web-chat users still need a browser or backend upload bridge.
| Name | Required | Description | Default |
|---|---|---|---|
| upload_url | Yes | ||
| content_type | No | ||
| local_file_path | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the burden. It clearly communicates a write operation (upload), a key prerequisite (server must be able to read the local path), and an environmental limitation (remote chat users cannot use it directly). It stops short of detailing presigned-URL expiration or failure modes, but those are largely implied by the presigned-URL mechanism referenced.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with the core operation front-loaded and the usage caveat following. Every clause adds distinct value, and there is no redundant filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The output schema is present, so the response format is covered externally. The description supplies the operation, the intended use case, and an important prerequisite. It could have explicitly named the upstream URL-generation sibling tool (video_assets_generate_presigned_url) and mentioned the 'content_type' parameter, but these are inferrable from schema and sibling names. Overall it is reasonably complete for a simple upload tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description must compensate for parameter meaning. It gives semantic hints for 'upload_url' (a presigned URL from the upload-URL endpoint) and 'local_file_path' (a file readable by the server), but it does not explain the 'content_type' parameter at all. Thus the compensation is only partial.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('Upload'), a specific resource ('local file from the MCP server's filesystem'), and a target ('presigned upload_url returned by the upload-URL endpoint'), making the tool's exact role unmistakable. It also distinguishes itself from sibling generation/download tools by focusing on the upload step.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit when-to-use guidance: 'local CLI testing when the server can read the file path', and when-not-to-use: 'remote web-chat users still need a browser bbackend upload bridge'. This is direct and actionable, though it has a slightly awkward sentence structure.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are differentiated by product-specific prefixes (e.g., lip_sync, text_to_video, image_upscaler), but the set contains many overlapping create_image/create_video tools, and generic editors like ai_image_editor_create_image and ai_video_editor_create_video blur boundaries with their more specific counterparts. Face/body swapping tools also occupy a similar conceptual space, requiring careful description reading to avoid misselection.
Names generally follow a descriptive snake_case pattern of feature plus action (e.g., text_to_video_create_video, image_projects_delete, wait_for_image_project). Minor inconsistencies like ai_face_editor_edit_image versus the dominant create_image suffix, and the mixed ai_ prefix usage across tools, prevent a perfect score.
44 tools is a large surface for an MCP server, even for a broad media-generation API. The count exceeds the 25+ threshold and creates a heavy selection burden, especially with over a dozen create tools for images and videos.
The surface covers the full create-to-download workflow for image, video, and audio: creation, status polling, wait helpers, fetch helpers, delete, and asset upload support. Minor gaps include no list/cancel endpoints and no general project search, but agents can complete core tasks without dead ends.
