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

Annotations already flag write, destructive, non-idempotent, closed-world; the description adds real behavioral detail beyond them: the operation is queued rather than synchronous, enqueues a specific worker, merges an optional updated timeline into the stored row, and requires polling afterwards. This is exactly the async/lifecycle context annotations cannot convey, and nothing contradicts the hints.

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 write/queued tag and the core action, then layers target, optional merge, and polling in a logical order. It is a single dense run-on paragraph with heavy parenthetical nesting, though almost every clause earns its place.

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 5-parameter mutation with no output schema and no annotation detail, the description covers identification, target selection, optional payload merge, and result retrieval — everything needed to fire the call correctly. Remaining gaps are the shapes of the two free-form object params and failure/retry behavior.

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 carries the full burden and largely does: it explains the id/uuid lookup pair, spells out the `video_render_target` sub-keys (storages_account_id or storages_account_uuid, optional video_render_target_path), and its conditional requirement. It is weaker on `video_project` and `video_output`, described only as an optional 'merged' edit with no hint of their shape, and it never says whether to prefer id or uuid when both are available.

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 ('Queue the render of a video') and immediately pins the identifying keys (`video_id` / `video_uuid`). The bracketed '[write, queued]' tag and the internal state transition (video_render_process=QUEUED -> worker_videos_render) tell an agent exactly what kind of operation this is, distinguishing it from sibling creation tools like create_video or replace_video.

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 makes clear this queues an async job and that the agent must poll the video row (video_render_process DONE/FAILED, plus video_render) for the result, which is actionable usage context. It also states the conditional rule for when `video_render_target` is required versus when the source account is used. What it lacks is explicit routing — no mention of when to prefer this over render_image, create_film_video, or retry_ugc_video.

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