Compare genomes

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

Annotations already declare readOnly, idempotent, and non-destructive behavior; the description adds meaningful context beyond that: rankings use the median in-scope percentile, high percentile is direction-dependent, and include_prompt attaches the same multi-sample LLM prompt as prs prompt/UI. This helps the agent interpret results and understand side effects.

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 main purpose and organized into focused paragraphs for inputs, ranking interpretation, and prompt behavior. It avoids obvious filler, though the internal 'just-prs' jargon and the conditional include_prompt detail keep it slightly above a minimal two-sentence description.

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 description covers the core workflow, input provenance, and ranking interpretation, and an output schema exists so return-value details are not required. However, five optional parameters have no schema descriptions and are not explained here, which leaves the tool incomplete for non-default use cases.

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?

The schema has 0% description coverage, so the description must compensate. It thoroughly explains result_paths (source, minimum count, grouping) and partially explains include_prompt, but leaves ancestry, assistant, model_scope, and genome_labels completely undefined. The required parameter is covered, but four optional parameters remain semantically opaque.

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 first sentence names a specific action ('Compare saved by-trait PRS reports') and resource ('two or more genomes'), clearly distinguishing it from computing PRS or building prompts. It also states the expected input type and grouping behavior, so the purpose is unambiguous.

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 clear context: result_paths must come from compute_prs_by_trait or saved report JSONs, at least two paths are required, and files are grouped by trait. It does not explicitly enumerate when-not-to-use cases or alternative tools, but the source requirement and one-call family-comparison note provide strong usage guidance.

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