compare_tracks

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

With no annotations, the description carries the burden and does disclose real traits: the isolation requirement and the refusal of full-mix fallbacks, plus that it captures audio and returns spectra/tables. It omits whether transport/playback must be running and what 'verified-isolated' entails, leaving some operational behavior unstated.

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?

Three dense sentences with the key constraint front-loaded and no filler. The 'for YOU to diagnose' emphasis is slightly informal but earns its place by clarifying the division of labor.

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 an audio-analysis tool with full schema coverage and no output schema, it covers inputs, output shape, and refusal behavior adequately. The main gap is that 'Same requirements as analyze_track' defers needed detail rather than stating it inline.

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 schema already documents 'tracks' (two or more names) and 'seconds' (default 30). The description's '2+' constraint largely repeats the schema's 'Two or more track names', adding no syntax or format detail, so baseline 3 applies.

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 (capture) and resource (2+ tracks' spectra plus a contested-band masking table), and implicitly differentiates from single-track analysis by referencing analyze_track requirements. The 'Post Mortem cross-track masking' framing is jargon-heavy but the core action is clear.

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 a clear precondition (2+ verified-isolated tracks) and an explicit when-not ('Full-mix fallbacks are refused'), plus a pointer to analyze_track for shared requirements. It stops short of naming a sibling to use instead for the non-isolated case, so it is not fully prescriptive.

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