edit_rewritten_script

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

With no annotations provided, the description carries the full behavioral burden and over-delivers: it discloses that the tool performs full-text overwrite ('本工具是全文覆盖' so unchanged scenes must be preserved verbatim), that it is free/instant/deterministic ('免费、秒级、结果确定不抽卡'), that it rejects calls for episodes never run through rewrite_script (400), and that damage is recoverable via get_script(include_previous=1). These traits go far beyond what the bare schema conveys.

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 front-loaded — the first line delivers the core decision (use this, not rewrite_script) before any workflow detail, and the numbered three-step guide with ★ markers keeps it scannable. Nearly every sentence adds distinct operational value given the tool's full-overwrite semantics; only minor redundancy (免费 appears twice) and the dense wall-of-text prevent a perfect economy score.

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 tool with no annotations and no output schema, the description covers the essential invocation knowledge: what to send (the full script), how to prepare it (get_script → selective edits → full resubmission), the failure mode (400), and the recovery path (include_previous=1). The remaining gaps are minor — the return value is never described, and episode_id semantics are implied rather than directly documented.

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 only 50% (episode_id has no description), but the description more than compensates: the script parameter gains critical semantics — it must be the complete rewritten script because the tool overwrites the whole document, and untouched scenes must be copied back verbatim rather than sent as fragments. episode_id also gets meaningful context: it must reference an episode that has already passed through rewrite_script, which is the precondition for success.

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 opens by naming the tool's exact role: ★改稿的首选通道(修改 AI 改写后的可拍稿) — the primary editing channel for AI-rewritten scripts. It names a specific verb (edit/write script_content), a specific resource (the rewritten script), and explicitly contrasts itself with rewrite_script, so an agent can distinguish it from its closest sibling without opening any 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 usage rule is explicit: '改写成功一次之后,所有修改都走这里,不要重跑 rewrite_script' — with the reasoning that rewrite_script restarts from the original and discards current fixes. It also states a hard exclusion (episodes that haven't run rewrite_script get a 400, so it's not a bypass channel for original scripts) and prescribes the exact 3-step workflow (get_script → edit only target scenes → resubmit full text).

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