lookup_variant

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

The description goes well beyond the readOnlyHint and openWorldHint annotations by disclosing that the tool is not implemented and will return error code 'unsupported' (E8). It also clarifies that the output contains no consensus or clinical verdict, which is essential behavioral information an agent could not infer from the schema or 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 consists of two tight sentences with no filler. It front-loads the core purpose, then immediately adds the two most important caveats: no consensus/clinical verdict and not implemented. Every clause contributes 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?

The description is adequate for a stub because it clearly tells the agent the call will fail, and the output schema exists to cover return values. However, it does not explain the valid parameter combinations or point to an alternative tool, leaving gaps for a hypothetical implemented version and for agents seeking a replacement.

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 only 17%, so the description needed to compensate, but it does not explain hgvs, rsid, variant, include, or assembly. The mention of ClinVar, gnomAD, Ensembl, and optional Atlas loosely hints at the sources parameter, but the primary variant-identification parameters remain entirely undocumented.

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 provides source-attributed evidence for a variant and names the external sources (ClinVar, gnomAD, Ensembl, optional Atlas). It also explicitly excludes consensus/clinical verdict, which helps distinguish its output scope, though it does not directly compare against sibling tools like get_variants or resolve_identifier.

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 'Not implemented in this build' warning and the 'No consensus or clinical verdict' exclusion give the agent clear signals about when not to use the tool. However, it names no alternatives and offers no explicit guidance for choosing this tool over sibling tools, leaving the positive use case mostly implied.

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