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

Annotations already declare readOnly and non-destructive, so the safety profile is covered. The description adds genuinely new behavior: download_url signals completion and a job idle for 45 minutes is marked failed without consuming quota, which tells the agent when to stop polling.

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?

Three short sentences, zero filler, with the core action front-loaded and completion/failure semantics following in priority order.

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 single-parameter poller with no output schema, the description covers what matters: the success signal and the timeout/failure condition. It stops short of describing other likely status fields (progress, error state), so a small gap remains.

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?

With a single parameter at 100% schema coverage, the schema already documents job_id as coming from create_music_video. The description adds nothing about the parameter, so the baseline 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: 'Poll a music-video job.' The 'music-video' qualifier implicitly separates it from get_clip_status and get_import_status, which poll other job types, though those siblings are never named explicitly.

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?

'Poll' plus the note that download_url appears when the MP4 exists makes the intended loop (repeated calls until a download URL appears) clear, and the 45-minute rule tells the agent how to interpret a stalled job. There is no explicit exclusion statement naming alternatives, which keeps it below a 5.

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