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

Annotations already declare the mutation profile (readOnlyHint=false, idempotentHint=false, openWorldHint=true), so the safety story is covered. The description adds genuinely non-obvious behavior the annotations don't carry: per-second credit pricing (from 25 credits/sec), a separate USD wallet for API keys, and a quote-then-confirm gate before charges. It does not disclose whether the call returns a job handle or is asynchronous, which matters for a long-running generation.

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 sentences, front-loaded with the core action, then pricing, then approval mechanics. Dense but every clause carries operational information; the billing explanation is somewhat compressed and could be split more cleanly.

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 7-parameter, open-world mutation with no output schema, the description covers cost, auth-path branching, and the confirmation gate well. The notable remaining gap is return behavior — whether a job id is produced and how to poll it (get_job siblings imply async).

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%, so the baseline is 3, but the description adds cross-parameter meaning the schema alone leaves implicit: which of max_credits (OAuth) vs currency + max_usd (API keys) applies to which auth path, and that no cost field should be supplied until a quote is confirmed. The 'omit approval' phrasing is slightly indirect since no parameter is literally named approval.

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?

'Continue a video: add a few more seconds after its last frame' is a precise verb + resource + mechanism, and the phrase 'after its last frame' cleanly separates it from create_video and edit_video in the sibling set. An agent knows exactly what operation this performs 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?

The description spells out the two-step approval workflow (omit approval to get a quote, then confirm max_credits or max_usd) and which billing path applies to OAuth vs API keys, which is real usage guidance. It stops short of explicitly naming when to choose this over create_video or compose_video.

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