prioritize_variants

Prioritize genetic variants by matching patient symptoms to HPO terms, identifying which variants most likely explain rare disease phenotypes using Exomiser analysis.

Instructions

Run Exomiser to prioritize patient variants by phenotype match. Provide HPO terms describing the patient's symptoms/conditions and Exomiser will rank which genetic variants most likely explain those symptoms. This is the gold-standard tool for rare disease variant prioritization. Requires Exomiser to be installed (npm run setup-exomiser). Returns nothing if Exomiser is not available — use other query tools instead.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`hpo_terms`	Yes	HPO term IDs, e.g. ['HP:0001250', 'HP:0000486']. Get terms from query_hpo.
`inheritance`	No	Inheritance mode filter: AD=autosomal dominant, AR=autosomal recessive, XL=X-linked, any=all modes	any
`max_results`	No	Maximum number of top-ranked genes to return

Tool Definition Quality

A4.6/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden and successfully discloses the external dependency (Exomiser), installation requirement, and silent failure mode ('Returns nothing'). Minor gap in not describing the success return format or safety profile (read-only vs destructive) given the lack of output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences with zero waste: purpose (sentence 1), usage/params (sentence 2), authority/context (sentence 3), and prerequisites/failure modes (sentence 4). Information is front-loaded and every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and no annotations, the description adequately covers prerequisites, failure modes, and sibling alternatives. Minor gap in not describing the structure of successful return values (e.g., ranked gene list format), though it implies ranking behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, establishing baseline 3. The description adds clinical context for hpo_terms ('describing the patient's symptoms/conditions'), enhancing understanding of what the parameter represents beyond the technical schema definition. Does not address inheritance or max_results, but adds significant value for the required parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('prioritize') and resource ('patient variants'), explicitly names the underlying algorithm ('Exomiser'), and distinguishes this from sibling tools by specifying it matches phenotypes to variants for rare disease cases.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use ('gold-standard tool for rare disease variant prioritization'), prerequisites ('Requires Exomiser to be installed'), and fallback strategy ('Returns nothing if Exomiser is not available — use other query tools instead'), providing clear decision boundaries against the many sibling query tools.

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

Install Server

Genomic-Agent-Discovery