Render

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

With no annotations the description carries the full burden well: it discloses external dependencies (ffmpeg on PATH or $ISMAIL_FFMPEG), a side effect (latest.wav is always written because analysis reads it), error behavior (bars outside the window raise), and muted sidechain tracks. It does not mention caching or idempotency behavior.

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?

Dense but front-loaded with the primary output location before sub-option details, and each clause adds a distinct fact. It is somewhat run-on across the middle, but no sentence is pure 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 7-parameter tool with 0% schema coverage, the description covers the important parameters, side effects, and dependency constraints, and summarizes returns. The unexplained cache parameter keeps it from being fully complete, though an output schema exists to cover the return shape.

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 0%, so the description must compensate, and it does for bars, tracks, stems, mp3 and out (via renders/<out>.wav), including the string values mp3 accepts. The cache boolean and the project parameter are left entirely unexplained, leaving a modest gap.

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 — render the project to renders/latest.wav or a named <out>.wav — and names the concrete output artifacts. It is clearly distinct from the surrounding analyze_*/cmp_* siblings that read audio rather than produce it, though it never contrasts itself with them explicitly.

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 per-option context: bars for a fast-iteration window, tracks to limit and keep sidechain sources silent, stems for per-track analysis, mp3='also' vs 'only' for output format. It never states when to prefer render over alternatives or any when-not conditions, 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.