enhance_shot_prompts

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

With no annotations provided, the description carries the full disclosure burden and meets it: it warns that prompts, including hand-tuned ones, will be rewritten; that it runs asynchronously; that it is paid for after the text step; and that doing it too late forces expensive regeneration. This is unusually explicit about side effects and cost.

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 tightly packed and front-loads the most important caveats (optional, side effects) before the effect and the timing warning. The use of parentheticals and ★ markers is a bit dense, but no sentence is wasted and the ordering supports decision-making.

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 single-parameter async mutation tool with no output schema or annotations, the description covers the essential operational context: effect, side effects, timing, optionality, async behavior, and payment. The main gap is the unexplained episode_id and the lack of any pointer to how async completion is observed, but the core calling decision is well covered.

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 0% and the lone required parameter episode_id is never explained. The phrase '全集 image_prompt' indirectly implies the target is an episode, but the description does not tell the agent that episode_id selects which episode's prompts will be enhanced, nor does it clarify expected input semantics beyond the integer type.

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 precise action ('AI batch enhance') and a clear resource ('the full set of image_prompt'), and adds critical scope qualifiers: optional, side-effectful, rewrites existing prompts, and must run before generate_frames. This makes it easy to tell apart from read-only prompt getters and later frame-generation steps.

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?

Gives explicit when/when-not guidance: only do it when a client explicitly requests it ('客户点名再做'), it is not required to complete an episode ('非跑通一部片的必需'), and it must be done before generate_frames because changing prompts after rendering stales images and wastes money. No alternative tool is named, but the decision to use or skip it is fully specified.

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