create_song

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 the vocal is NOT rendered, that both outputs are length-matched at 0:00, and that a soundfont is only used if FluidSynth is installed (otherwise a built-in synth renders). It omits write-location/overwrite behavior and any failure modes, which keeps it short of a 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?

The two-sentence summary is front-loaded and states the core contract before the per-parameter notes, and each parameter line is compact and earns its place. It runs long overall, but the length is driven by genuinely non-obvious parameter syntax rather than filler.

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 file-generating tool with no output schema and no annotations, the description covers the returned artifacts, their alignment, and the external dependency (FluidSynth) plus the required follow-up step in UTAU. The main remaining gap is the undocumented half of the parameter set (tempo, style, drums, output_dir, etc.).

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% across 19 parameters, so the description must compensate. It richly documents lyrics (syllable/held-note syntax), chords ('|', '%', looping), key, lyric_mode (with per-mode semantics), voice_range, guide_volume, seed, and soundfont — but leaves bass, drums, style, tempo, instrument, name, intro_bars, bars_per_line, beats_per_bar, voice_dir, and output_dir entirely unexplained.

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?

Opens with a specific verb and resource ('Turn lyrics and a chord progression into a song') and names the concrete artifacts produced (.ust plus .mid/.wav backing of matching length). This implicitly distinguishes it from siblings lyrics_to_ust and render_backing, which each produce only one of those outputs.

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?

The description explains the post-generation workflow ('open the .ust in UTAU or OpenUtau with a voicebank, and import the backing .wav alongside it'), which clarifies the intended pipeline. However, it never states when to choose this tool over lyrics_to_ust or render_backing, so the alternative-selection guidance is only implied.

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