Sound Zoom

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

With no annotations, the description carries the burden and does well: it discloses the exact analysis settings (256-point/32-sample hop vs 2048-point), a non-obvious caveat that the time-sharp boundary sits 50 ms early, that both panels share one fixed plot box so a box maps to identical pixels, and that a .json sidecar beside the PNG maps pixel to (s, Hz). What it omits is the mutating side: whether/where a file is written and whether out controls that path.

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?

The core idea is front-loaded, but the middle sentences are dense run-ons that pack window sizes, hop, ms offsets, and pixel-mapping into single clauses, and jargon like 'spectrogram's eye mode' assumes prior knowledge. Every fact is arguably useful, yet the packing slows an agent's parse rather than wasting words.

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?

An output schema exists, so return values needn't be explained, and the visual/behavioral story is rich. The gap is input coverage: three of nine parameters (project, source, out) are undocumented by both schema and description, which for a 0%-coverage schema leaves real ambiguity about what file is being examined and where output lands.

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% across 9 parameters, so the description must compensate, and it covers only part: it explains seconds=[t0, t1], f_lo..f_hi in Hz, words=[{'w','t0','t1'}] in seconds, and ruler in ms, and implies bars via 'inside bars'. It says nothing about project, source, or out, leaving key inputs undefined in both places.

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 concrete verb+resource+output: a time x frequency box of a sound at two resolutions, stacked in one PNG, with the top panel time-sharp and the bottom frequency-sharp. It explicitly names the sibling it surpasses ('when spectrogram's single view blurs the edge') and the follow-up tool (sound_zoom_diff), so an agent can place it precisely among siblings.

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?

States the trigger condition directly ('Reach for it when you need to zoom into one word, hit or note and see both its timing and its harmonics') and names the alternative it is chosen over (spectrogram's single view). It also routes the comparison workflow to sound_zoom_diff, covering when to use that instead.

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