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

Adds meaningfully beyond the annotations: a 200 MB size cap, the direct-file-link requirement, and that it is free. Annotations already cover mutability and non-idempotence, so the remaining gap is what happens after upload (asset id vs. job) and whether the import is asynchronous.

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 sentence, front-loaded with the action and the constraint, followed by the purpose and cost. Nothing is wasted and nothing important is buried.

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 import with no output schema, the description covers input constraints, cost, and intended downstream use. It could be complete by stating what the call yields (an asset reference or a job to poll), which an agent will need to chain into other tools.

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 baseline is 3, and the description earns above that by adding the 200 MB size limit and reinforcing that it must be a direct https link to the person's own media rather than a page URL. Type scope (video/audio/picture) is also restated usefully.

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?

Specific verb ('bring in') plus resource ('video, audio or picture') with the key qualifier that it must be the person's own media from a direct https link. This distinguishes it from the generation siblings like create_video, create_image, and create_song without having to compare schemas.

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?

Gives the downstream reason to call it ('so other tools can use it: a clip to remake, a song to remix or extend, a photo to animate') which effectively points at remake_*, edit_*, and extend_* as follow-ups. It stops short of an explicit 'use this instead of create_* when the media already exists' exclusion.

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