normalize_loudness

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

With no annotations, the description carries the burden and does add key traits: it is non-destructive ('Doesn't modify audio data'), it operates on items via volume rather than audio, and it discloses a version requirement. It omits error behavior and whether the change is undoable, leaving a moderate gap for a mutation tool.

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 core action and non-destructive note, then groups parameter guidance compactly. No filler sentences; every clause adds 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?

No output schema exists and none is needed, but the description omits what the call returns and how failures are reported. For a project-mutating command with no annotations, that is a small residual gap given how thoroughly parameters and mechanism are covered.

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 does: it enumerates all `kind` values with the default, gives representative `target_db` values, and spells out the `selected_only` boolean semantics. Every one of the three parameters gains meaning absent from 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 and resource ('Normalize the perceived loudness of items') plus the mechanism (adjusting each item's D_VOL volume). This clearly separates it from siblings like set_track_volume_db, which set a raw level rather than a loudness target.

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?

Provides concrete scenarios for choosing values ('-14 for streaming, -23 for broadcast EBU R128') and a prerequisite ('Requires REAPER 6.40+'). It does not name an explicit alternative tool or a when-not condition, 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.