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

Annotations already declare non-readOnly, idempotent, non-destructive. The description adds substantial behavioral context beyond that: the -20/-14 LUFS targets, -2 dBTP codec-safe ceiling, a latency-compensated hard ceiling, application to preview AND export, and project-scoped identity return. The one gap is that it never states how this interacts with per-clip volume/gain (set_volume/set_audio_gain).

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 PROJECT-SCOPED constraint and the core two-stage description, then defaults, overrides and opt-out in logical order. It is dense and uses heavy all-caps emphasis, but nearly every sentence carries distinct operational meaning; only mild 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?

With no output schema and a 2-parameter boolean/id tool, the description covers defaults, overrides, opt-out, scope, effect stages, and points to project_state for verification. Nothing an agent needs 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 coverage is only 50% because 'enabled' has no schema description, but the description compensates thoroughly, spelling out the semantics of enabled=true (force on any format) and enabled=false (raw opt-out). It also reinforces project_id scoping as an explicit immutable parameter, matching the schema note.

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 (master the mix to a loudness target), defines the two-stage behavior (dialogue leveled to -20 LUFS, final mix to -14 LUFS), and clearly distinguishes itself from gain/volume siblings by describing loudness normalization rather than level adjustment. An agent can tell what it does 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?

Explicitly states when a call is NOT needed (9:16/4:5/1:1 and 'source' portrait are mastered by default) and when to force it (enabled=true for a quiet 16:9 YouTube export) versus the explicit opt-out (enabled=false for raw sound when the user asks). This is textbook when/when-not guidance.

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