Compare

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

With no annotations, the description must carry the behavioral load; it discloses that output covers similarity metrics, worst bars, and advice, which tells the agent the shape of the analysis. It says nothing about whether comparison is non-destructive, cost, or alignment implications of offset_b, leaving real behavioral gaps.

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 tight sentences with the core compare action front-loaded, followed by a compact metric list. Slightly dense with unexplained jargon terms, but no 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 excuses explaining return values, and the description does enumerate the scoring dimensions. But with six undocumented parameters, no annotations, and heavy sibling overlap, it stops short of what an agent needs to invoke this correctly.

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 define all six parameters. It only illuminates 'a' and 'b' (defaults plus the 'track:bass'/'ref:bass' stem syntax); 'bars', 'detail', 'offset_b', and 'project' are never explained, so the agent is left guessing at scope, granularity, and alignment offset.

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 ('compare two sources bar by bar on the project grid') and clarifies the default operands (your render vs the reference). However, it does not distinguish itself from the many sibling comparison tools (cmp_run, cmp_bars, cmp_summary, sound_compare), so an agent cannot tell which comparator to pick.

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 through the named default case (render vs reference) and the stem-comparison example, which shows a concrete invocation pattern. But there are no when-to-use/when-not statements and no routing relative to the cmp_* or sound_compare siblings.

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