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

Beyond the read-only and open-world annotations, the description discloses monthly-release sourcing, inclusion of the VCF header, overlap-based record selection, and tabix block-limited fetching. These details add useful context about data currency, output shape, and retrieval efficiency, though operational limits such as remote failures or rate limits are not discussed.

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?

A single front-loaded sentence conveys the operation, source, output contents, and retrieval mechanism without filler. It is dense but remains readable, and each clause contributes distinct 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?

Together with the fully described input schema, output schema, and safety annotations, the description supplies what is needed to invoke the read correctly: region scope, native header-and-records output, overlap semantics, and indexed retrieval. Assembly defaults, coordinate bases, and record caps are already covered by the schema, so their absence from the prose is not a gap.

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 100%, including coordinate conventions, assembly choices and default, and the max_records cap with truncation reporting, so the baseline of 3 applies. The phrase 'every record overlapping the region' adds useful selection semantics, but the description otherwise leaves individual parameter explanation to the schema.

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 opening phrase identifies a specific read operation, resource, release cadence, and region scope, while 'as the VCF ClinVar publishes' clarifies that the result is the native VCF. It does not explicitly contrast itself with siblings such as lookup_variant or read_variant_calls, so it falls short of the top sibling-differentiation bar.

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 'one region' and native-VCF wording establish a clear use case: obtaining ClinVar's published header and overlapping records for a single locus. There is no explicit when-not guidance or alternative for processed variant lookups or multi-region work, which prevents a 5.

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