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

Annotations already establish this as a safe, idempotent, non-destructive read, so the description's job is to add operational detail — and it does: the 30 MB size ceiling, the exact multipart field name 'video', and the upload_id in the response. It omits things like accepted video formats or URL expiry, which is why it is not a 5.

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?

A single dense sentence with zero filler; the size limit and field name come first and the downstream consumers are named at the end. Every clause carries information an agent needs.

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 parameterless tool with no output schema, the description covers what is returned (an upload URL plus upload_id) and what the upload_id is for. It does not explain the format of the returned URL or the upload mechanism, leaving a small gap for an agent that must actually perform the multipart POST.

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?

The tool takes zero parameters, so the baseline is 4. The description does add useful semantics for the subsequent upload call by specifying the multipart field name 'video', which the schema cannot express.

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 and resource ('Returns an upload URL for a video file') plus the concrete constraint of 30 MB and the multipart field name 'video'. This differentiates it from the sibling upload_image, which handles images rather than videos, without needing to open 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?

The description clearly routes the agent forward by naming the two consumers of the returned upload_id: create_carousel_from_video and video_to_idea. It does not give an explicit exclusion (e.g., 'use upload_image for images'), so it falls short of a full when/when-not statement.

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