start_video

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

With no annotations present, the description carries the full burden and does so well: it discloses the async job model, expected polling cadence (~30s) and duration (1-5 min), the fact that retries are charged twice, the https-only URL constraint, and that estimate_only starts nothing and charges nothing. Almost no behavioral gap remains for a job-launching tool.

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?

The start-and-poll instruction is correctly front-loaded and every sentence carries non-redundant information - no filler. It is dense and parenthesis-heavy, though, which slightly hurts scannability for an agent parsing modality branches.

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?

No output schema and no annotations, yet the description covers the return value (job_id), the polling loop, typical completion time, the timeout/retry hazard, and cost caveats. For a 9-parameter async-launch tool, nothing needed to call it correctly is missing.

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 description coverage is already 89%, so the baseline is 3. The description adds real meaning beyond the schema by mapping parameters to model families and conventions - i2v for image_url, Veo/Kling/Seedance for end_image_url, r2v plus the 'character1, character2…' prompt convention for reference_urls, and audio-capable models for sound. It does not, however, add anything for duration or aspect_ratio beyond what the schema states.

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 ('Start an asynchronous AI Gateway video') and immediately pairs it with the return contract ('return a job_id immediately'). The follow-up instruction to poll get_video makes it distinguishable from generate_image, edit_video, and extend_video without opening any 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?

Explicitly routes by modality: prompt-only for text-to-video, image_url for i2v, end_image_url for first-to-last-frame, reference_urls for r2v with named characters, and sound for dialogue. It also names the alternative action on timeout ('do not call it again... let them decide'), which is exactly the when/when-not guidance an agent needs.

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