measure_loudness

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

With only readOnlyHint=true available, the description adds substantial behavioral context beyond annotations: it runs a render dry run, writes no files, restores selections, adds no undo step, and discloses the non-obvious side effect that measuring the master marks the project modified. That caveat is exactly the kind of trait annotations cannot express.

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 blocks — what it measures, how the target/range work, and what it returns — with the metric list front-loaded and zero filler. Every sentence carries information the agent cannot get from schema or annotations.

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 read-only measurement tool with no output schema and undocumented parameters, the description is complete: it covers metric definitions, target/range semantics, side effects, and the full return field list including the approximate/unavailable note. Nothing needed to invoke or interpret 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 description coverage is 0%, so the description carries the load and mostly does: start_time/end_time limit the measurement range, track_index selects a track or defaults to master, and item_index measures one item's track output with other items muted. It leaves minor ambiguity (e.g., whether item_index is global or per-track, that -1 means master), keeping it out of the top score.

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 (measure loudness) and enumerates the exact metric set (integrated LUFS, short-term/momentary max, LRA, sample peak, true peak). It also distinguishes itself from the sibling measure_spectrum by naming the loudness-window behavior, so an agent can tell them apart without opening either 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 defines the target choices (master default, a track, or one item) and the start_time/end_time scoping condition, which is real when-to-use guidance. It stops short of naming alternatives or exclusions against measure_spectrum, so it is clear context rather than full routing guidance.

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