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

Goes well beyond the readOnly/idempotent annotations: it discloses the BS.1770 K-weighting standard, that stored levels are combined with volume keys/gains/fades/ducks, the windowing (400 ms momentary, 3 s LRA windows), that parts under 3 s have no LRA, that '-' means silence, and that it uses no credits. These are exactly the computational and cost facts an agent cannot infer from annotations or schema.

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 and front-loaded — the core output definition comes first, then behavior, then the null-sentinel rule, then cost, then the sibling pointer. The nested parentheticals ('each value the 400 ms before its time', 'the sounds' levels summed where they are loudest, not a sample peak') make it a single heavy paragraph that could be split or trimmed slightly.

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?

There is no output schema, so the description carries the full burden of describing return values, and it does: per-lane and mix momentary LUFS at 0.5 s intervals, integrated LUFS, LRA in LU, and true peak in dBFS, plus the null/silence conventions. Nothing an agent needs to interpret the result 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 100%, so the baseline is 3, but the description adds real semantics the schema lacks: passing null for both startSeconds and durationSeconds reads the whole film (a joint-behavior detail not in either field description), plus the film-seconds unit and the '-' silence sentinel. Only a modest increment above baseline, hence 4.

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?

Opens with a specific verb+resource ('Loudness of the composed timeline's sound over time, as numbers') and immediately enumerates the exact readouts produced. It distinguishes itself from the analysis/read siblings by naming read_render as the tool for a finished render's sound.

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 an explicit workflow ('measure, change the keys, measure again') that tells the agent this is a pre-render iteration tool, and names the concrete alternative for post-render measurement ('For the same readout of a finished render's sound, call read_render with loudness true'). When-to-use and when-to-use-something-else are both present.

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