normalize_audio

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

With no annotations the description carries the full burden. It usefully discloses the two-pass method, that video streams are copied untouched, and that before/after loudness is reported, but it does not say whether the source file is modified in place, whether audio is re-encoded, or how costly a two-pass run is.

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?

Three short sentences, each earning its place: capability first, then the non-destructive guarantee, then the reported result. Nothing is padded or repeated from the schema.

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 single-step media mutation with four well-documented parameters and no output schema, the description covers purpose, side effects on video, and the return signal. Only format/support limits and source-file mutation semantics remain unstated.

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 100%, including an explicit LUFS mapping for each target value and the overwrite default, so the schema already does the heavy lifting. The description adds no syntax or default detail beyond calling out the delivery-target concept, so the baseline 3 applies.

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 a recording's loudness') plus the exact method (EBU R128, two-pass loudnorm) and target concept. 'Video is copied untouched' separates it cleanly from transcoding siblings like convert or compress, and from denoise which addresses noise rather than level.

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?

The stated goal ('narration and system audio are neither too quiet nor clipping') implies the situation it is for, but no sibling alternative or exclusion is named and no prerequisites (e.g. audio track must exist, run before or after denoise/music_bed) are given.

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