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

Annotations already declare readOnly/non-destructive, yet the description adds substantial behavior: what is deliberately not exposed (prompts, provider details, private media), the retry backoff contract, the 'accepted/running ≠ completed' pitfall, and the fact that replacements are new paid attempts. This is well beyond the annotation surface.

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 purpose, then ordered guidance ending with per-case special handling (Seedance Draft, Audio). It is long and clause-dense, but each sentence carries actionable content rather than 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?

No output schema exists, so the description carries the return contract itself and does so thoroughly: status, failure/refund state, retry object with afterSeconds and arguments, retry null, library/workspace destinations, lineage eligibility, expiry, finalJobId and finalizationAvailable. An agent has what it needs to act on and interpret the response.

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 0% and the single jobId parameter is undocumented in the schema. The description implies it identifies 'one known owned generation' but never states the id's origin (e.g. from prepare_generation) or accepted format, so it only partially compensates for the coverage gap.

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 with scope: 'follow or recover one known owned generation'. That cleanly separates it from list_recent_generations (enumeration) and present_generation (delivery), so an agent can pick it without opening the 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?

Explicit when-to-use triggers (after interruption, ambiguous submission response), explicit stop condition ('when retry is null, stop automatic polling'), and explicit routing to siblings (retry.tool, present_generation, refund inspection). Exclusions and alternatives are all named.

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