Upload video from URL

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

With no annotations, the description carries the full disclosure burden and succeeds: queued/asynchronous processing, three accepted link types (including the KIT player edge case returning an already uploaded video), an explicit failure mode (400), size and format acceptance, content-based deduplication, the response contract (video ID), and a pollution workflow. This meets the bar that annotations would otherwise have to cover.

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?

Five dense sentences are arranged in a logical narrative (purpose → accepted inputs → failure condition → limits → occupancy). Nothing duplicates schema content and each clause delivers a constraint or next step, so the length is all functional signal rather than padding.

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?

For a one-parameter tool with no output schema, nothing is missing: input format, failure condition, limitations, and the full downstream playback (poll get_video to READY, attach via media, one video per variant, required co-existing image). An agent can go from a bare URL to a correct API call purely from this text.

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?

Schema coverage is 100%, so the baseline is 3. The description enlarges the schema by adding an agent-relevant constraint: the link must be reachable without authentication or the API answers 400, and it restates the accepted link forms in operational terms. Modest but genuine value beyond the schema.

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 names a precise verb, resource and method: 'Upload a product video by public link and queue it for processing.' It immediately differentiates itself from the sibling upload_video ('use it instead of upload_video when the file lives on the web'), so an agent can select between the two upload tools without opening either schema.

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?

Reference explicitly states when to use it: instead of upload_video when the file is web-hosted rather than local. It also gives operational preconditions (link must be public, no auth, else 400) and a follow-up protocol (poll get_video until READY, attach through media in create_variant/update_variant). That is a complete when/how routing package.

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