Genomic-Agent-Discovery

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

No annotations are provided, so the description carries the full disclosure burden. It successfully adds interpretation context for the return values (score thresholds), but omits operational details such as error handling for invalid rsIDs, data source limitations, or whether the operation is idempotent.

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?

Two sentences with zero waste. The first front-loads the core purpose (lookup), while the second provides essential interpretation context. Every word earns its place; no filler or redundancy.

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?

For a simple single-parameter lookup tool without output schema, the description is nearly complete. The critical addition of score interpretation (PHRED >20 meaning) compensates somewhat for the lack of return value documentation. Could be improved by noting error cases or return structure.

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?

With 100% schema description coverage ('dbSNP rsID'), the schema fully documents the single parameter. The description mentions 'variant' which aligns with the rsID parameter, but adds no additional semantic detail about parameter format or validation beyond what the schema already provides. Baseline 3 is appropriate.

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?

Description clearly states the specific action ('Look up'), resource ('CADD score'), and target ('variant'). It expands the acronym CADD and specifies the exact biological database being queried, distinguishing it from sibling query tools like query_alphamissense or query_clinvar.

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?

Provides valuable interpretation guidance ('PHRED-scaled scores above 20 suggest top 1% most deleterious variants') that helps the agent understand result significance, but lacks explicit guidance on when to choose this tool over sibling variant annotation tools like query_alphamissense or prioritize_variants.

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