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

With no annotations, the description carries the full behavioral burden and does it well: it discloses the side effect (downloading and writing a file to the output directory), the 60-second cap, and critically that ai mode fails loudly with a specific missing-component message rather than silently falling back to original. It also reveals that the script auto-selects pitch and reports it back via `pitchNote`.

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-loaded with the pipeline in a single sentence, then mode semantics, then the pitch warning — a sensible ordering. It is fairly dense with no filler, though the pitch auto-tuning point is partially restated from the schema description rather than fully earning its space.

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?

No output schema exists, but the description still names the key return values (filename, and pitchNote in ai mode), which is the essential information for chaining to a voice-send tool. It leaves minor gaps such as what happens when no song is found or whether the output file is overwritten, but nothing blocking for correct invocation.

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 the baseline is 3; the description adds real guidance by telling the agent not to guess `pitch` and to leave it blank for auto-tuning, rather than leaving the agent to interpret the -24..24 range itself. It also reinforces mode semantics beyond the enum labels, though it adds nothing about `candidate`, `startSeconds`, or `seconds` beyond what the schema says.

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?

Names a specific verb and artifact (sing a clip) and lays out the concrete pipeline: search online → download source → clip ≤60s → write to output dir → return filename. The two modes are defined distinctly, so an agent can tell exactly what the tool produces without opening the 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?

Gives clear conditions for each mode (original = source clip, ai = RVC voice conversion requiring a ready local model) and names sing_search as the way to preview candidates before setting `candidate`. It also tells the agent the follow-up step (send via the bot framework's voice tool). It does not mention sing_probe or when this tool is the wrong choice, so it stops short of full routing guidance.

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

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 this is a diagnostic probe over external binaries, GPU availability, model assets, and directory writability, which tells the agent it may be slow and environment-dependent. It omits an explicit statement that it is read-only / side-effect-free, which would have closed the gap fully.

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 check list, then explains the three return fields, then ends with the usage cue — a logical order with no filler. The component enumeration is long but each item is a distinct thing an agent may need to report back, so it earns its space.

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?

There is no output schema, so the description must explain return values, and it does: aiReady, aiMissing, and originalReady are each defined along with their meaning for whether a cover or original segment is possible. Combined with the enumerated checks, an agent can call it and interpret the result without anything else.

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?

Zero parameters, so the baseline is 4; the description correctly spends no words on input arguments and instead allocates them to output interpretation, which is the right trade for a no-arg tool.

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+resource ('检查唱歌链路是否就绪') and enumerates exactly which components are probed: yt-dlp, ffmpeg, torch/CUDA, demucs, RVC project, voice model, contentvec, output-dir writability. That makes it clearly separable from siblings sing_search and sing_cover, which perform the actual singing work rather than the pre-flight check.

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 to call it first when confirming 'can I sing right now', which anchors its place relative to sing_cover. It stops short of naming the siblings or stating when not to call it (e.g. after a known-good run), so it is clear but not fully routing.

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

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

With no annotations, the description carries the burden and mostly succeeds: it discloses the fallback behavior between two sources, the shape of returned candidates, and a genuine operational trap (short clips that start mid-chorus). It does not state failure behavior when nothing is found, latency, or any limits, though these are minor for a read-only search.

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?

Core capability and source strategy are front-loaded in the first clause, followed by return fields and selection advice. The clip warning is slightly verbose but earns its place by preventing a real failure mode; only minor tightening is possible.

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 2-parameter search with no output schema and no annotations, the description covers what is returned, how to choose among candidates, and what to do next. It omits empty-result behavior and any hint about sing_probe, which keeps it from a 5.

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 100%, so both query and limit are already documented in the schema. The description adds no format or constraint detail beyond the schema's own example, so the baseline of 3 applies.

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?

Uses a concrete verb+resource (在线搜歌) and immediately narrows the scope with its source strategy (B站优先, YouTube 兜底) and the exact fields returned (标题/时长/播放量/链接/上传者). An agent knows exactly what it gets back and can distinguish it from sing_cover, which is positioned as the downstream step.

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 routes the agent: when unsure which version, call this first, then call sing_cover. It also supplies concrete selection heuristics (prefer high view count, 1.5–8 minute full tracks; avoid 切片/片段/翻唱/live clips). The one gap is sibling sing_probe — the description never says when that tool is the better choice.

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