record_audio

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

With no annotations, the description carries the full burden. It discloses realtime capture, soloing behavior with state restoration, system prerequisites, fallback behavior, and return value. However, it could be more explicit about side effects like automatically starting playback or potential failure modes, so a 4 is appropriate.

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 description is moderately long but dense with essential information. Each sentence contributes prerequisites, workflow, or parameter guidance. It could be tightened slightly, but the length is justified for an 11-parameter tool.

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?

Despite missing parameter details, the description is contextually complete for the core usage: it explains prerequisites, workflow, duration selection, source selection, and return path. With an output schema existing, the return format is covered. The main gap is the unexplained advanced parameters, but overall it's a well-rounded description for a complex tool.

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 compensate. It explains source, scene, bars/seconds, and position_beats meaningfully. However, 6 of 11 parameters (solo, device, out_path, tail_seconds, tighten_launch, preroll_seconds) remain unexplained, leaving gaps for an agent to infer their semantics. This is a clear gap given low schema coverage.

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 clearly states the tool captures Live's audio output to a WAV via a loopback device, specifying a verb, resource, and output format. It implicitly differentiates from siblings like analyze_audio/compare_audio by suggesting the output feeds into them, but it does not explicitly distinguish from record_and_analyze, so it loses a point.

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?

Provides concrete guidance on choosing duration (bars vs seconds, prefer 2-4 bars), selecting source (track index vs master/return), and scene configuration (Session vs Arrangement). It gives clear context for the main workflow but does not explicitly state when to use an alternative like record_and_analyze, so it does not earn a 5.

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