Genomic-Agent-Discovery

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It successfully adds domain context by explaining that HPO terms represent 'clinical phenotypes (symptoms, findings)' and mentions they are 'linked to variants,' helping the agent understand the data relationship. However, it lacks disclosure about return format, pagination, or data freshness that would be valuable given the absence of annotations and 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.

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

The description consists of two efficient sentences. The first establishes the core function, and the second provides essential domain context (defining HPO terms as clinical phenotypes/symptoms). Every sentence earns its place; there is no redundancy or extraneous 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?

For a single-parameter query tool with full schema coverage, the description adequately explains the tool's purpose and domain. However, given the lack of output schema and annotations, the description could be improved by briefly characterizing the return value (e.g., a list of phenotype terms) to complete the agent's understanding of the tool's contract.

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 input schema has 100% description coverage (the 'gene' parameter is documented as 'Gene symbol'). The description references 'a gene' and 'variants in this gene' which aligns with the parameter usage, but does not add significant semantic depth beyond the schema's 'Gene symbol' definition. Baseline 3 is appropriate since the schema already fully documents the parameter.

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 states the tool 'Find[s] Human Phenotype Ontology terms associated with a gene' and explains that these are 'clinical phenotypes (symptoms, findings).' It uses specific verbs (find, shows) and resources (HPO terms), and explicitly references the clinical/symptom domain, distinguishing it from sibling tools like query_gene or query_disease_genes that may return general or disease-specific gene data.

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?

While the description implies usage context by mentioning 'clinical phenotypes' and 'symptoms,' it provides no explicit guidance on when to use this tool versus alternatives like query_gene or query_disease_genes. It does not state prerequisites, exclusions, or selection criteria.

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