record_audio_sample

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

With no annotations, the description carries the full burden and does reasonably well: it discloses that recording blocks for the requested duration, that the .wav defaults to a temporary file, that the return includes a signal-level analysis (RMS/dBFS), and how to pick an ALSA device. It omits failure behavior when no capture device exists and any permission/device-busy caveats, which matters for a hardware-touching tool.

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?

It is front-loaded with the verb, resource, and output format, then follows with a scoped Args block, so the agent can stop reading once it has what it needs. The usage-suitability sentence sits between the summary and the args, which is slightly better placed at the end, but nothing is genuinely wasted.

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 5-parameter, zero-annotation hardware tool, the definition covers purpose, every parameter's semantics and defaults, and the analysis it returns, with no output-schema gap to fill. The remaining hole is operational: no stated behavior on a missing or busy capture device, and no note on whether the recording can be interrupted.

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 must fully compensate, and it does: it gives the duration range (1 to 30, default 5.0), the unit for sample_rate (Hz, default 16000), the mono/stereo meaning of channels, the temp-file default for output_path, and concrete ALSA device string examples ('default', 'hw:0,0', 'plughw:1,0'). This is meaning well beyond the bare schema titles and defaults.

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 description gives a specific verb and resource — record microphone audio for `duration_sec` seconds and analyze RMS/dBFS — plus a concrete framing ('verifying hardware audio output (speaker -> host mic)') that separates it from siblings like play_test_tone or set_audio_volume. An agent can identify this as the capture/analysis tool without inspecting the 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?

It supplies clear usage contexts (speaker-to-mic loopback verification, testing a USB microphone), which is genuine when-to-use guidance. It stops short of explicit exclusions or naming alternatives such as play_test_tone or list_media_devices, so routing between the audio siblings still requires inference.

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