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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds substantive context the annotations cannot convey: the results are curated and clinically interpreted, and each variant carries an evidence count plus associated diseases and therapies, which tells the agent the payload is pre-summarized rather than raw.

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?

Two tightly packed sentences with the resource and its distinguishing value front-loaded; almost every clause carries information. 'Pass the gene symbol' is mildly redundant given gene is required and schema-documented, but it usefully confirms the primary invocation input.

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 no output schema, the description must carry return-value information, and it does: variant types, evidence counts, diseases, therapies. It omits any mention of the 25-default/1-100 limit behavior or ordering, but the schema covers the limit bound, so nothing essential for a correct call is missing.

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%, so all three parameters are already documented by the schema, establishing a baseline of 3. The description reinforces the required gene symbol but adds no syntax or semantics beyond the schema for limit or the variant_name substring filter.

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?

Names a specific resource (curated CIViC variants of a gene) and enumerates the alteration types returned (missense, fusion, amplification, exon-level), so the agent knows exactly what comes back. It distinguishes itself from civic_variant_evidence and civic_assertions implicitly through the 'which variants exist' framing, but never names those siblings, so differentiation is inferential rather than explicit.

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 'AUTHORITATIVE for "which variants of this gene are clinically actionable"' line gives a clear use context, and 'Pass the gene symbol' states the invocation prerequisite. There is no when-not guidance or named alternative for the adjacent tools (civic_variant_evidence, civic_assertions, civic_search_genes), which keeps it below a 5.

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