normalize_loudness

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

With no annotations, the description carries the burden well: it discloses that only the used portion is measured, that ducking keyframes are preserved by shifting the whole curve, that gains are capped at +15 dB, and that dryRun is non-committal preview. It stops short of stating permissions, undo behavior, or what dryRun actually returns, so it falls just shy of full transparency.

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 action and the dialogue/music split are front-loaded in the first sentence, followed by caveats (ducking, +15 dB cap, dryRun) and the export_deliverables hand-off. Dense but every clause carries information; the nested parentheticals with defaults make it slightly harder to scan.

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 an 8-parameter mutation tool with no annotations and no output schema, the description covers defaults, the gain cap, keyframe handling, preview mode, and the relationship to export. Still missing are return shape for dryRun and edge-case behavior (no audio tracks, clips already at target, mixed music/dialogue classification).

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 88%, so baseline is 3, but the description adds real semantics: it explains the dialogue-vs-music target logic, the 'music alone goes to target' exception, and what dryRun does. sequenceId/sequenceName/track list selection is left entirely to the schema.

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 ('Even out clip loudness on the timeline') and immediately specifies the mechanism: measure LUFS on the used part of each clip and set its Volume level. It also carves a distinct role versus siblings like set_clip_volume and adjust_audio_levels by describing a measurement-driven, per-clip normalization pass.

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?

Makes clear when to reach for it (dialogue/voice at target, music tucked under voice) and points to dryRun for previewing measurements. It also explicitly defers platform-level loudness to export_deliverables, preventing double-normalization confusion, though it never explicitly contrasts with adjust_audio_levels or setup_ducking.

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