music_apply

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

With no annotations, the description carries the full burden and does well: it discloses that audio is downloaded into the project, that a scene object is created, and critically that re-invocation REPLACES the previous track — a destructive side effect an agent must know. It omits error/permission conditions (e.g. what happens with no open project, download failures), keeping it at 4 rather than 5.

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?

Front-loads the core action and equivalence, then parameters, then next steps — a logical order with no filler sentences. It is a single dense block of clauses rather than clearly separated segments, which slightly hurts scanability but wastes no words.

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 mutating tool with five parameters, no annotations, and no output schema, the description covers what an agent needs: the action, the replacement semantics, the clipping behavior, the ID provenance constraint, and the verification/persistence follow-ups. Missing only failure modes and whether the audio download is slow or rate-limited.

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 100%, so all five parameters are already documented. The description adds only modest meaning: that start_sec/end_sec jointly define a clip with 'default whole song', and that music_id must be sourced from music_list in this session (partly already in the schema). This is the baseline-3 case where the schema does the heavy lifting.

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 and resource ('把一首抖音音乐设为特效的音乐') and immediately anchors it to a known UI action ('和音乐库里点「使用」相同'), then enumerates the three concrete effects: download audio, write music info, add a Douyin music object to the scene. This distinguishes it from siblings like music_list (discovery) and library_apply (non-music library assets).

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 a hard prerequisite ('music_id 须来自本会话的 music_list') and a follow-up workflow ('之后 capture_preview 验收、save_project 落盘'), which tells the agent how this tool fits into a sequence. It stops short of naming an alternative tool for other music sources or stating an explicit when-not-to-use condition, so it is not a full 5.

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