Genomic-Agent-Discovery

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

No annotations provided, so description carries full burden. Discloses critical behavioral details: multi-database cross-referencing and the two-step workflow (find variants → check patient carriage). Missing safety/performance traits (rate limits, auth requirements), but core behavioral logic is transparent.

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?

Three sentences with zero waste: sentence 1 defines core action, sentence 2 defines patient-specific filtering, sentence 3 provides usage guidance. Perfectly front-loaded with the most critical information.

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?

Adequately explains the multi-source aggregation workflow for a moderately complex tool. Given no output schema exists, absence of return value documentation is acceptable, though inclusion would strengthen completeness further.

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 has 100% description coverage with clear examples ('BRCA1', 'CYP2D6'). Description mentions 'gene' in context but adds no semantic information beyond the schema. Baseline 3 appropriate when schema documentation is complete.

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?

States specific action ('Find ALL known variants') and resources (ClinVar, GWAS, AlphaMissense). Explicitly distinguishes from siblings like query_clinvar or query_gwas by emphasizing the cross-referencing/aggregation behavior across all three sources simultaneously.

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?

Explicitly positions the tool as 'the best starting point for investigating a specific gene,' providing clear entry-point guidance. However, lacks explicit 'when not to use' guidance or named alternatives for specific use cases (e.g., when you only need single-database data).

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