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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds genuine behavioral value beyond annotations: the 'Variants not found in the database are marked with found=false' disclosure tells agents how missing data is signaled, and the chromosome-mixing note clarifies no position grouping is required. 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?

Four dense sentences, each earning its place: purpose and inputs, return payload, use cases, then behavioral notes. The main action is front-loaded in the first sentence, and no word is wasted. It is compact yet information-rich.

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 batch tool with a 1000-ID limit, two accepted ID formats, and field selection, the description covers inputs, outputs, error signaling (found=false), and flexibility constraints. An output schema exists so return-value details are covered elsewhere. The only gap is explicit routing to or away from sibling tools (single-variant lookup versus this batch endpoint), which is implied by the title but never stated.

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 description coverage is 100%, and both the ids and fields parameters already carry rich descriptions including accepted ID formats, the 1000-ID maximum, default field list, and response-size guidance. The tool description reinforces this same information (formats, max limit, return fields) without adding new parameter semantics, so the baseline 3 applies.

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 opens with a specific verb and resource: 'Retrieve annotations for up to 1000 genetic variants in a single request.' It clearly distinguishes this batch tool from the myvariant.variants.search, .info, and .metadata siblings by its batch scope, ID-based input, and 1000-variant limit. An agent can tell exactly what this tool does and how it differs from the single-query variants.

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?

The description gives concrete use cases ('annotating VCF files, enriching GWAS hit lists, building polygenic risk score pipelines, or bulk pharmacogenomics analysis') and the 'Mix rsIDs from different chromosomes freely — no grouping by position required' line removes a common preprocessing concern. It does not explicitly name sibling alternatives or state when NOT to use it (e.g., for a single variant call), which keeps it from a 5.

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