Assess quality

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

Annotations declare readOnlyHint=true, consistent with the description's 'no I/O' claim. The description adds behavioral context by detailing how match_rate, auroc, and percentile are combined into a human-readable interpretation. No contradictions.

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 concise with two short paragraphs. It uses backticks for the parameter name and clearly separates input explanation from output description. No extraneous text.

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 tool's low complexity (3 params, 1 required) and the presence of an output schema, the description adequately covers the core functionality. It explains the primary input and the nature of the output. Minor gaps: no mention of valid ranges or edge cases for inputs.

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. It defines match_rate as 'the fraction of scoring variants matched (0-1)' and notes that auroc and percentile are optional with default null. However, it does not explain the meaning or impact of auroc and percentile on the output, leaving some ambiguity.

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 clearly identifies the tool's purpose: classifying and interpreting a PRS result's quality. It specifies the main input (match_rate) and outputs (quality label/color, interpretation). The phrase 'pure logic — no I/O' distinguishes it from sibling tools like compute_prs that perform I/O.

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 implies the tool is for assessing quality of a PRS result, and the mention of 'pure logic' suggests it is safe to call without side effects. However, it does not explicitly state when to use it over siblings like best_performance or percentile, or provide exclusion criteria.

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