Audio features

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

Annotations only say this is not read-only, is open-world and non-idempotent; the description goes well beyond that by disclosing the run-accounting semantics ('nothing is uploaded', 'does not count as another run', 'one run' for a file_path) and where output lands (`metadata` under `song`/`sections`, plus the results folder). That is the exact cost/side-effect context an agent needs before triggering a compute job.

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 measurement list, then the invocation routes, then value interpretation — a sensible order with no filler sentences. The energy/danceability explanation is slightly discursive and the hard line breaks make it read as fragmented, but every clause carries information.

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 two-optional-parameter compute tool with an output schema, the description covers the prerequisite (segment), the two mutually exclusive input modes, the cost model, and where results appear. There is no auth or failure-mode discussion, but nothing required to invoke it correctly is missing.

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%, and the schema already explains both parameters including the file_path-triggers-segment behavior, so the description is largely restating it. What it does add is interpretive meaning for the measured values (0-1 ranges, LUFS, per-section measurement making a drop read higher than its breakdown), but that is output semantics rather than parameter semantics.

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 enumerates the measured quantities (energy, danceability, loudness, mode, key, tatum) at both song and section granularity. It also scopes itself relative to `segment` ('can run straight after segment', 'needs no stems'), though it never distinguishes itself from the sibling `analyze` tool, which an agent may plausibly confuse it with.

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 lays out the two input routes — reuse `analysis_id` from a segment result (no upload, no extra run) or pass `file_path` (segment runs first, one run). The prerequisite and cost consequence of each are stated, which is exactly the guidance an agent needs. No exclusion against alternatives like `analyze` or `tag_audio` is given.

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