Live Parity

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 that it runs a silent engine, states the runtime cost ('about as long as rendering the bars twice'), and quantifies result interpretation ('-100 dB and below is identical; under -80 dB nobody can tell'). The edge-bar caveat is genuinely useful nuance. It stops short of operational details like side effects or permissions, hence not 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 the framing question, which is good, but the body is dense and rambling with stacked clauses and parentheticals that could be trimmed. Every idea is relevant, but the delivery is longer than needed for the information conveyed.

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?

An output schema exists so return values need not be explained, and the description covers the core mechanics and interpretation thresholds well. The main gap is the undocumented song parameter and lack of explicit routing against similar comparison tools.

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 and only partially does: bars is described as the window [a, b] and the second-bar judgment rule, and tracks is explained as limiting both sides. The song parameter is never explained, leaving one of three params undocumented anywhere.

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 comparison operation — rendering bars in the studio versus playing them on a silent deck — and names exactly what it compares (tracks, buses, mix) across named dimensions (level, envelope, octave bands, residual). This is clearly distinguishable from the analyze_*/cmp_* and live_* siblings.

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 implicitly tells the agent it does not need live_start and that nothing is late, which orients it against the live_* siblings. However it gives no explicit when-to-use versus alternatives like compare, cmp_run, or cmp_bars, so the usage context is only implied.

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