audio_capture

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

With no annotations, the description carries the full load and does most of it: nothing gets installed, existing output routing is untouched, transport/playhead are restored, metronome and precount are silenced, and the capture is audible. It does not mention macOS audio-capture permission prompts or failure modes (no audio playing, tap denial), which is the main behavioral gap for a system-level recorder.

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-loads the core action and mechanism, then layers conditional behavior; nearly every clause carries information. Some sentences are long and semicolon-chained, but there is no filler.

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 capture tool with no annotations and no output schema, the description covers side effects, defaults, and cleanup behavior well. It never states what is returned (the written path, duration, or a confirmation), which an agent needs since no output schema exists.

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 coverage is 75%, and the description adds real meaning on top: 'out' defaults to the studio-one-mcp data folder, and from_seconds/from_bars act as alternatives used only when transport is stopped, falling back to the playhead. It does not restate the 600-second cap or clarify how from_seconds and from_bars interact if both are supplied.

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?

Names a specific verb and resource (record what Studio One plays to a WAV file) plus the mechanism (macOS process tap) and format (32-bit float, session rate). The line 'Never records in Studio One' explicitly separates it from the live_record / live_bounce siblings, so an agent can select it without opening 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?

Gives the downstream handoff ('Pass the file to audio_analyze') and the exact behavior when transport is stopped, which tells the agent it can call this at any time. It stops short of naming alternatives it competes with (e.g. live_bounce for an in-app offline render), so the exclusion is only implied.

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