Sound Import

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

With no annotations, the description carries the full burden. It does usefully disclose a non-obvious behavior: pre-import diagnostics that warn when peaks are flattened or high-frequency content is missing, before the sound is measured or played. But it says nothing about whether importing an existing name overwrites, whether the bank is mutated persistently, or what permissions/context are required.

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?

Two dense sentences that front-load the core action and source vocabulary, with the warning behavior following as secondary detail. Minor density in the parenthetical source list, but nothing is 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?

The presence of an output schema means return values need no explanation, and the warning behavior is well covered. Still, for a 7-parameter mutation tool with zero annotation coverage and 0% schema descriptions, the missing semantics for name, project, and normalize leave real gaps before an agent can call it confidently.

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 0%, so the description must compensate. It defines 'source' with concrete examples and clarifies that start_sec/end_sec are seconds while bars is a grid pair [a, b] — covering 4 of 7 parameters. It leaves 'name', 'project', and notably 'normalize' entirely unexplained.

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 ('Import audio into the bank') and enumerates the accepted source forms (ref, ref:vocals, track:x, render), which makes the tool's input domain concrete. It does not name or contrast with likely siblings such as sound_extract, sound_make, or sound_compare, 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?

The description implies usage context by describing optional time-slice and bar-range selection, and it explains what the tool validates. However, it never says when to prefer this over sound_extract or sound_make, nor does it state prerequisites (must the source already be analyzed?).

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