Assess quality

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

Annotations already declare readOnlyHint=true and idempotentHint=true, lowering the bar. The description adds behavior context beyond annotations by explaining the tool's core logic: it combines match rate, AUROC, and optionally result percentile into a quality label/color and interpretation, and it echoes low-coverage caveats. This goes beyond simple read-only claims and details what the tool actually computes.

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 reasonably concise and front-loaded with the core purpose. The additional paragraph about parameter provenance and return structure earns its place, as it clarifies how to pass percentile-derived fields. It's slightly dense with backticks, but the content is structured and not redundant with the schema.

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?

With an output schema present, the description doesn't need to detail return values, but it does explain what the interpretation combines and how the summary derives from passed parameters. It covers the core inputs and logic, and provides important context about the dependency on the percentile tool. Given the tool's moderate complexity, the description is sufficiently complete for correct invocation.

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 match_rate as 'the fraction of scoring variants matched (0-1)', and references AUROC, result percentile, percentile_method, reliable, and caveat, indicating their roles in the interpretation. While it doesn't formally define each parameter, it gives enough meaning for an agent to understand how the parameters relate to the output.

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 opens with a specific verb+resource: 'Classify and interpret a PRS result's quality (pure logic — no I/O).' This clearly distinguishes it from sibling tools by emphasizing that it performs pure logic with no I/O, and the resource (PRS result quality) is precise. The rest of the description reinforces the purpose by explaining what it returns (label/color and interpretation).

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 gives explicit workflow guidance: 'Pass percentile_method / reliable / caveat from the percentile tool so the summary describes how the percentile was actually derived.' This tells the agent when to use this tool (after obtaining percentile output) and how to wire it. It doesn't explicitly name alternative tools or say when not to use it, but the 'pure logic — no I/O' hint and reference to the percentile tool provide sufficient context for selection.

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