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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, and the description still adds real context: long-form jobs take many minutes (timing/latency expectations) and a completed job yields a link. It also discloses post-completion UI behavior (panel offering scene animation or 3D shot review), which an agent could not infer from structured fields.

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 core action, followed by the timing caveat and the no-loop rule; every sentence carries information. The final sentence about panels is long and slightly convoluted, but it is not 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, the description must carry return-value burden. It explains the success case (a link once ready) but never says what comes back while the job is still in progress (status string, progress, error states), which is exactly what a polling tool returns most of the time.

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% and the single parameter is fully documented in the schema ('Job id from create_video. Omit for the most recent video.'). The description adds no additional meaning about video_id, so the baseline of 3 applies.

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: 'Check how a video is coming along and get the link once ready.' An agent can distinguish this status-poll from create_video, update_video, and the other check_* siblings without opening the schema. It stops short of naming an alternative explicitly, so it is clear but not fully differentiated.

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 an explicit usage condition ('Call when the user asks') and an explicit prohibition ('not on a loop'), which is the key failure mode for a polling tool. It does not name a sibling alternative, but there is no real substitute for a status check, so the guidance is effectively complete.

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