update_project_settings

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

With no annotations, the description carries the behavioral burden and does well: it discloses that the tool is free ('免费') and, crucially, that changing worldview brief/ethnicity/aspect ratio/consistency anchors does NOT retroactively update existing content – regeneration is required. It does not cover response format, partial-update semantics, or reversibility, but the key side-effect warning is present.

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?

A single dense paragraph that front-loads the purpose and then organizes the large parameter space into categories (visual anchors, audio, subtitles, transitions) before adding the cost and regeneration caveats. It is compact for a 52-parameter tool, though the punctuation-heavy style makes it slightly harder to parse.

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 complex settings-update tool with no output schema or annotations, the description covers the scope, cost, and the most important side-effect (no automatic refresh of already generated content). It does not specify partial-update semantics or what happens to audio/subtitle/transition changes on existing episodes, but the breadth and warning make it reasonably complete for invoking the tool.

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 only 62%, so the description partially compensates by grouping parameters into meaningful categories and naming key fields (cinematography_prompt/art_bible/visual_lock, bgm_source/bgm_volume_preset/use_clip_audio, show_subtitles/subtitle_secondary_lang, etc.). However, roughly 38% of parameters lack schema descriptions and the tool description does not explain those fields either, so an agent would still need to infer semantics for undocumented params.

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 action ('建剧后修改项目设定' – modify project settings after drama creation) and enumerates the covered categories, ending with '即项目设定页全部通用设定' (all general settings on the project settings page). It clearly differentiates from create_drama and per-shot editing tools, though it does not name a sibling explicitly. The '除…外' phrasing is slightly ambiguous (could be read as 'except' vs 'in addition to'), but the schema and '全部通用设定' clarify the inclusive intent.

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?

Explicitly says the tool is for modifying settings after the drama has been created ('建剧后') and scopes it to the full project settings page, which distinguishes it from creation tools and per-shot/per-scene editing tools. It lacks explicit when-not-to-use guidance or named alternatives, but the context is clear enough.

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