export_stems

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

Goes well beyond annotations by explaining that rendering is offline/faster than real time, that each stem is a soloed track including send returns but excluding the master chain unless through_master, the file naming pattern, and that the tool returns a job whose result lists files (valuable since no output schema exists). It does not address file-overwrite behavior or failure cases, but annotations already cover the non-destructive safety profile.

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 action and output ('Render one WAV per track ... into a folder') and every clause carries information. The opening sentence is long and multi-clause, which slightly hurts readability, but nothing is redundant.

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 file-writing operation with no output schema, the description covers the essential gaps: the return value (a job with a result file list), the exact file naming, and the default stem composition. Overwrite semantics and prerequisite that the folder must exist are left to the schema, which is acceptable given full schema coverage.

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 the baseline is 3, but the description adds substantive meaning: what a 'stem' includes compositionally, what through_master actually changes about the output, and that 'tracks' defaults to every non-group track. It adds no detail for dither, bit_depth, or start/end beats, leaving those entirely to 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 specific verb and resource: 'Render one WAV per track ... into a folder', which unambiguously identifies per-track stem export. It does not, however, distinguish itself from siblings like export_render (presumably a full mixdown) or audio_split_stems (separation of imported audio), so an agent must infer the boundary.

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 is implied by 'all audible tracks, or the ones listed' and the master-chain toggle, giving a sense of when this is the right export mode. But there is no explicit when-to-use/when-not guidance and no named alternative (export_render, audio_split_stems), so routing remains inferential.

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