upload_video

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

Annotations already establish readOnlyHint=false and idempotentHint=false, but the description adds non-obvious behavior: Vimeo pulls the file itself, the call returns immediately with a video id while transcoding continues, and the video is not playable right away. It also discloses the auth requirement (upload scope), which is information no structured field provides. No contradiction with annotations.

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?

Four sentences, each earning its place: purpose, constraint, async behavior, and auth requirement. The most decision-relevant information (what it does and how) is front-loaded, and the auth note is efficiently tucked at the end. No filler or repetition of schema content.

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?

Given the async nature and absence of an output schema, the description adequately covers the return behavior (immediate video id, not playable yet) and the key precondition. It stops short of describing failure modes (e.g., unreachable URL response) or suggesting a follow-up like get_video to track transcoding status, which would round out the picture for an agent.

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?

Adds meaning beyond the schema for the only required parameter: 'Vimeo pulls the file itself' explains why the url must be publicly reachable, complementing the schema's brief 'Publicly reachable URL' note. The other four parameters rely on schema descriptions and enum values, which are adequate even though the description doesn't elaborate on them. At 60% schema coverage, the description compensates for the most critical parameter, which is exactly where agents need the extra context.

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?

States a specific verb (upload), resource (video to Vimeo), and method (giving a public URL to fetch), which distinguishes it clearly from siblings like list_videos, update_video, and add_videos_to_folder. The fetching mechanism is stated up front, so an agent immediately knows this creates a new video resource rather than operating on an existing one.

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?

Provides clear precondition for use: the URL must be publicly reachable, not a local path — which tells an agent when this tool is viable versus when it isn't. It doesn't explicitly name alternatives, but no sibling directly competes for this operation (upload_texttrack is the closest cousin and targets a different resource), so explicit exclusions aren't necessary.

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