Get Curations for Many Diseases

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

The description adds behavioral context beyond annotations: it explains that unresolved inputs are returned in 'unresolved' without failing the call, and that result blocks mirror the singular version. No contradictions with annotations.

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 extremely concise—two sentences that cover purpose, usage, behavior, and parameters without any 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?

Given the tool's complexity (batch operation, partial failure, multiple parameters) and presence of an output schema, the description covers the essential aspects: input constraints, error handling, result structure, and parameter usage. It is nearly complete.

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?

Despite low schema description coverage (33%), the description adds meaningful semantics: it specifies the max batch size for diseases, explains limit_per_disease as capping genes, and describes response_mode as controlling detail. This compensates for schema gaps.

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 it is the batch form of get_disease_curations, accepting a list of disease IDs or titles (max 20) and returning gene assertions for each. It distinguishes itself from its singular sibling and other curation tools.

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?

It explicitly mentions the batch nature and references the singular form, implying use when multiple diseases are needed. It also provides guidance on parameters. However, it does not explicitly exclude use cases for alternative tools like find_curations or get_genes_curations.

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