audio_view

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real behavioral value beyond that: the on-canvas semantics (horizontal lines = harmonics, vertical stripes = transients, haze = noise), the red 0 dBFS clipping markers, and the fact that save_to writes a PNG to disk. The disk write is the one detail an agent should reconcile with readOnlyHint, but it is a requested new artifact rather than a mutation of source data, so no contradiction is claimed.

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-loaded with the core purpose, then kind options, then an interpretation legend. Nearly every sentence carries information an agent needs to read the rendered image or set parameters, though the spectrogram-reading tutorial is on the verbose side for a tool description.

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?

Against 8 parameters with zero schema descriptions and no output schema, the description supplies the render semantics, the interpretation legend, and most parameter behavior, so an agent can invoke it correctly and understand the returned image. The unexplained max_freq/freq_scale/path params are the only meaningful omission, and they have usable defaults.

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 whole burden and does substantial work: it enumerates the kind values, explains start/end as zoom bounds, defines pitch_overlay, and notes save_to's side effect. Gaps remain for max_freq, freq_scale (default 'log') and path, which are completely undocumented in both the schema and the description.

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?

The opening clause states a specific verb and resource: render a picture of the sound, then enumerates the three render kinds ('both', 'waveform', 'spectrogram'). This clearly separates it in spirit from data-oriented siblings like audio_analyze, audio_melody or audio_transcribe, but no sibling is named, so routing is inferred rather than explicit.

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?

Usage mechanics are covered well ('Zoom with start/end', 'pitch_overlay draws the detected f0 in cyan', 'save_to optionally also writes the PNG to disk'), which tells the agent how to shape the output. However there is no guidance on when to choose audio_view over audio_analyze, audio_info or audio_events, and no stated prerequisites (file must exist locally, supported formats).

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