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

Annotations already carry the safety profile (readOnlyHint=true, openWorldHint=false), so the lower bar applies. The description does add genuinely useful behavior — this is a polling/blocking call with the terminal states COMPLETED and FAILED — but it omits the worst case: with maxAttempts up to 180 at 30s, a call can block for ~90 minutes, and nothing warns about that or about what happens when attempts are exhausted.

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?

Only two sentences, but the second is a near-verbatim restatement of the first ('until COMPLETED or FAILED' appears twice), so half the text earns nothing. The interval detail should have been replaced with parameter and return-value information.

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 exists, so the description must explain what comes back when the job completes or fails — it does not (status field? asset URL? error reason?). Combined with undocumented parameters and no timeout/retry semantics, an agent cannot confidently call this for anything beyond the happy path.

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% for all three parameters, so the description had to compensate and does not: generationId, maxAttempts, and intervalSeconds are never explained. Worse, 'Checks every 30 seconds' states a fixed interval as fact while intervalSeconds is configurable (2–60), which misdirects the agent rather than helping it.

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?

Specific verb and resource: 'Poll a voiceover or change_voice job' — it names both the resource and the sibling job type (change_voice) it also covers, which helps distinguish it from audio_status or wait_for_video. It stops short of explicitly routing against the other wait_for_* siblings, but the purpose is unambiguous.

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?

Usage is implied — call it after creating a voiceover or change_voice to block until the job settles. There is no explicit when-to-use/when-not guidance, no mention of the non-blocking alternative (audio_status, list_generations), and no guidance on what to do on timeout or on re-calling after FAILED.

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