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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the bar is lowered; the description still adds meaningful context beyond them: output is decision-support with explicit limitations, the tool does not evaluate patient context, results must not be framed as diagnosis/treatment, and it refuses to select a candidate when resolution is ambiguous. These are behavioral traits that materially shape how an agent should invoke and present the results.

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?

Six sentences, each carrying distinct information: usage triggers, scope, input forms, return contents, safety limitations, and ambiguity policy. It is front-loaded with the highest-value routing information and, while slightly verbose, the density is justified for a medical-reasoning tool with safety implications.

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 complex ACMG/AMP classification tool, the description covers what to pass, what comes back, scope limits, and safety constraints, with an output schema available to document return structure. An agent has everything needed to decide when to call it and how to responsibly handle the result.

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%, so the baseline is 3; the query and assembly parameters are already well documented in the schema. The description adds useful scope constraints not fully explicit in the schema (germline SNV or simple indel <50 bp, GRCh38-only), but it mostly restates accepted input forms already enumerated in the query parameter description.

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 explicit user-intent triggers ('classify or interpret pathogenicity, review a VUS, check available ClinVar assertions or population-frequency evidence, or resolve a variant notation') and states a precise scope: one public GRCh38 germline SNV or simple indel smaller than 50 bp. This clearly differentiates it from the literature-oriented siblings (search_variant_literature, get_publication_details), which concern publications rather than variant interpretation.

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?

Provides explicit 'Use when...' triggers covering classification, VUS review, evidence checking, and notation resolution, plus a clear exclusion: it does not evaluate patient context and must not be presented as a diagnosis or treatment recommendation. It does not explicitly name sibling literature tools as alternatives, but 'Never choose a candidate when resolution is ambiguous' adds practical guidance on when to abstain from answering.

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