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

Annotations already declare readOnly, idempotent, non-destructive, open-world, so the safety profile is covered. The description adds genuinely new behavior: ambiguous assembly/transcript is reported rather than guessed, and predictions retain source and uncertainty. It could still say more about cache behavior beyond the 'freshness' schema field and about partial source failures.

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?

Front-loaded with the core action and identifier forms, then defaults, then optional extensions, ending with a concrete example. Every clause carries information; the only redundancy is restating the id formats already in the schema.

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?

With an output schema present and annotations covering safety, the description needs to explain invocation choices, and it does: defaults, opt-ins, ambiguity policy, uncertainty retention. Pagination behavior for the civic/gwas section parameters is left to the schema, which is reasonable.

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 coverage is 83%, putting the baseline at 3, and the description slightly exceeds it by explaining that listed source/section names are opt-in additions and by exemplifying the id format. However, the id-format sentence largely duplicates the schema's own `id` description, so the added meaning is modest rather than rich.

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 a specific verb and resource ('Get evidence for one variant') and enumerates the accepted identifier forms, including an example. The single-variant, multi-source aggregation scope implicitly separates it from search_records/query_source, but no sibling is named explicitly, so an agent still has to infer that boundary.

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?

Useful operational guidance is present: the default source set (ClinVar, gnomAD population, CIViC) and the opt-in additions for predictions, cosmic, oncokb, hotspots, gwas, cbioportal. What is missing is when to prefer this over get_record or resolve_entity, and whether resolution should happen first for ambiguous IDs.

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