generate_videos

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses auto-abort on insufficient balance, rejection when no first frame exists, review-token invalidation after content changes, default error blocking, and potential wasted charges/defective output if acknowledge_review:true is used carelessly.

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?

The description is long but appropriately dense for a multi-gated tool, with clear ordering: main action, prerequisites, review gate, and quote confirmation. Each sentence carries distinct operational value, and visual markers (★, ⚠️) help the agent prioritize critical constraints.

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?

Despite no output schema and no annotations, the description covers preconditions, rejection causes, failure behavior, the review workflow, token lifecycle, quote flow, and post-invocation polling. An agent has enough context to invoke the tool correctly and route the user through the required confirmation steps.

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?

Beyond the schema's 75% parameter coverage, the description adds operational meaning: quote_id must come from an approved quote with estimated_points relayed to the user, review_token is tied to review_frames findings and can expire after content edits, and acknowledge_review should only be true when the customer explicitly insists despite errors. This goes well beyond the bare schema descriptions.

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?

The description clearly states the tool's action: '确认后批量出视频' and '一条后台链跑完整集', defining it as batch full-episode video generation after confirmation. It distinguishes itself from single-shot generation tools through explicit batch/full-episode wording and the polling instruction via get_storyboards.

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?

It gives explicit when-to-use guidance: must call review_frames first, must call a quote_* tool first and obtain explicit user consent, and must use the returned quote_id. It also tells the agent what to do next ('用 get_storyboards 轮询 video_url') and warns against self-confirming quotes or overriding review errors on the user's behalf.

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