Ear Pass

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

With no annotations, the description carries the behavioral burden and explains the composite comparison flow, the crops behavior, and the conditional default for stems. It does not explicitly state side-effect safety, latency, or cost, but it discloses enough operational behavior for an analysis tool.

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?

The description is front-loaded with the purpose, but the core explanation is a dense run-on sentence packed with internal tool references and parenthetical clauses. It avoids obvious filler, but the structure makes it harder than necessary to scan.

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?

Given the composite behavior, five parameters, zero schema description coverage, and no annotations, the description covers most of what an agent needs, including usage context and key defaults. It loses some completeness by not explaining the required project parameter or how the reference is identified.

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 description coverage is 0%, so the description must compensate. It explains stem values, the top-bar limit, the crops behavior, and the conditional stems default, but it leaves the required project parameter unexplained and omits the top default of 3.

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?

The description states a specific composite operation: a full comparison of the latest render with the reference, including worst-bar ranking, band differences, zoom, and optional crops. It also distinguishes the tool from component siblings such as cmp_run, cmp_worst, cmp_zoom, region_measure, and sound_zoom by saying this happens 'in one call.'

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?

It gives clear usage triggers: 'Reach for it before each draft goes to the person' and when a note names a quality you cannot place by ear. It also says this is the comparison the render reply asks for, though it does not explicitly state when to prefer the individual cmp_* tools instead.

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