从上传剧情由Pavo生成分集

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

Even with annotations present, the description adds substantive behavior: it consumes quota, requires per-session generation authorization, and does not auto-confirm the outline. It also states that the source file must still exist and be unchanged, and that it will not download URLs or re-upload. That is exactly the operational context an agent needs before invoking a costly generation task, and it is consistent with openWorldHint=true and destructiveHint=false.

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 purpose and the key precondition come first, followed by exclusions and the quota/authorization caveat, so the ordering is sensible for a single dense sentence chain. It is tight overall, though the semicolon-chained clauses pack several distinct facts together, and the reference to a non-existent 'requirements' field is wasted text.

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?

An output schema exists, so return values need no explanation, and the mutation/quota/auth profile is well covered. The remaining gap is the input side: with 0% schema coverage, an agent still cannot tell what 'ratio' or the nested 'style' object should contain, which is material for a tool that spends quota on generation. Adequate but incomplete for a five-parameter generative mutation.

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% for five required parameters, including a nested style object, so the description carries the full burden and largely fails to meet it. It constrains planned_episode_count to 1-100 and implies upload_operation_id comes from a prior upload receipt, but ratio, style, and operation_id are never explained, and 'requirements' is mentioned without a matching parameter. Only partial compensation 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?

The description uses specific verbs and a clear resource: verify the local source file's SHA from a successful upload receipt, extract the story, and call the official-site AI to generate episodes. It also distinguishes this tool from the full-script parsing path (projects/upload 完整剧本解析) and from re-uploading. It loses a point for referencing 'requirements', which is not among the five schema parameters, creating mild ambiguity about what is actually being submitted.

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 a clear precondition (a successful upload receipt from this account, source file still present and unmodified), an explicit 'don't' (no downloading arbitrary URLs, no re-uploading, no full-script parsing), and a scope limit (1-100 planned episodes). What it does not do is name a sibling alternative such as pavo_script_import_text or pavo_script_create_ai and state when an agent should choose those instead.

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