export_audio

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

With no annotations, the description carries the full burden and does well: it discloses the return shape (a path plus capture metadata, not inline bytes), the failure mode ('Reports silent captures instead of writing a silent file and claiming success'), and the required precondition of active playback. It does not discuss overwrite behavior, export directory location, or duration limits, which keeps it from a 5.

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 purpose, then alternative routing, then format semantics, then precondition, then an example — a sensible order. A few phrases are stylistically loose ('not a wall of base64', 'claiming success') but they carry behavioral information rather than padding.

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 five-parameter, zero-required capture tool with no output schema, the description covers return values, format tradeoffs, the silent-capture edge case, and the playback precondition. Remaining gaps — where files land, overwrite behavior, and session routing — are either minor or already handled by the schema's parameter descriptions.

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 100%, so baseline is 3, but the description adds real meaning beyond the schema: 'format=wav (default) decodes to 16-bit PCM a DAW will open; format=webm writes the raw Opus recording' explains the consequence of each enum value rather than restating it. It also demonstrates filename usage in the example call, though it says nothing extra about output=base64 or session_id beyond the schema.

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?

States a concrete verb and resource — 'Record a window of live Strudel audio and write it to a file' — and immediately differentiates itself from the sibling audio_capture by saying it is preferred 'when you want the audio to exist somewhere.' An agent can pick between the two without opening either 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 an explicit alternative ('prefer this over audio_capture') with the condition that selects it, plus a hard prerequisite: 'Audio must already be playing: call playback({ action: "play" }) first.' That is when-to-use, when-to-use-something-else, and ordering guidance in two sentences.

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