get_storyboards

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

No annotations are provided, so the description carries the full burden. It thoroughly discloses the returned status model (frame_status/video_status enums, fail_reason categories, retryable semantics, fail_hint), special cases (not_required, external uploads bypassing the quality chain, reopen_pair_id), and the fact that the call is free. This is far more transparent than a typical getter.

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 dense but well-structured, using ★ markers to separate special cases and front-loading the primary purpose. Every sentence carries operational value—status interpretation, retry policy, external-upload caveat, reopen_pair_id. It is longer than a simple getter, but the complexity of the returned statuses justifies the length.

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?

With no output schema, the description carries the return-value burden and covers the major fields: first_frame_image, video_url, frame_status/video_status, fail_reason, retryable, fail_hint, source markers, and reopen_pair_id. It does not mention pagination or shot-level identifiers, but for the tool's review/progress purpose this is largely complete.

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?

The schema provides episode_id with zero description coverage, and the description compensates by opening with '读某一集的分镜列表', making clear the parameter selects which episode's storyboards to read. It does not explicitly walk through the parameter, but with a single integer ID the semantics are unambiguous.

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 (读/read), resource (某一集的分镜列表/storyboard list of an episode), and purpose (审阅/查进度). The mention of per-shot first frame, video readiness, and structured statuses distinguishes it clearly from sibling tools like get_storyboard_table_spec or review_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?

Provides clear context for when to use it (review/progress checking) and gives substantial operational guidance: treat not_required as complete, decide retry vs content change based on retryable, and route external-upload drift to generate_shot_frame. It does not explicitly name alternative tools, but the usage context is strong and actionable.

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