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

Annotations only say it is a non-read-only, non-destructive operation, but the description discloses far more: async execution returning a task_id, dedup behavior (same file completes with the existing clip), storage accounting, backend 1080p editing-copy creation, and the irreversible consequence of keep_original:false ('the clip is 1080p from then on'). This is exactly the behavioral context annotations cannot carry.

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?

Front-loaded with the import action and its input constraint, and almost every clause carries new information (dedup, task polling, editing copy, keep_original). It is dense and semicolon-chained rather than bulleted, making it harder to scan than it needs to be, but there is little pure 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?

With no output schema and 0% schema coverage on seven parameters plus an async workflow, the description does substantial work: it covers the return contract (task_id → get_task → generation_id), dedup, cost, storage, and the original-retention tradeoff. The unexplained name/prompt/project_id parameters are the remaining gap.

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 0%, so the description must carry the load; it explains density (quick|normal|detailed, 180 s cap, credit cost), metadata (own fields, 4 KB max, returned on reads), keep_original, and the url constraint. However name, prompt, and project_id are never mentioned, leaving three of seven parameters undocumented anywhere.

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?

Opens with a specific verb+resource: 'Imports a video FILE from a link', and even scopes the accepted input ('a direct .mp4/.mov/.webm url, not a page that plays it'). It is clear this is an import rather than a generation, but no sibling such as generate_video or add_image is named, so the contrast is left implicit.

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 clear applicability context (direct media URL, any size storage allows) and an explicit negative case ('not a page that plays it'), plus the operational path of polling get_task until complete. It never states when to prefer generate_video or add_image instead, so alternative-routing guidance is absent.

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