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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds real context beyond that — tiering schemes, FDA companion-test flags, regulatory-approval flags — telling the agent what kind of content comes back. Pagination/return-size behavior is left to the schema's limit param.

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?

Dense but front-loaded: the resource identity and the authoritative-use signal come first, filters last. Slightly heavy on qualifiers, but every clause earns its place by clarifying scope or actionability.

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 the return-value burden, and it does reasonably well by naming the tiering frameworks and regulatory flags the assertions carry. Missing only minor details like result ordering or default paging behavior, which the schema partly covers.

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 four parameters (limit, disease, therapy, molecular_profile) are already documented with examples. The description only restates the filter dimensions ('Filter by molecular profile, disease or therapy') without adding format or matching semantics, so baseline 3 applies.

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+resource ('CIViC assertions — the curated, AMP/ASCO/CAP-tiered and ACMG-classified clinical summaries') and explicitly distinguishes itself from the evidence-item siblings by describing the roll-up relationship ('roll up multiple evidence items into a single actionable statement'). An agent can tell it apart from civic_variant_evidence without opening either schema.

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?

Explicitly frames the use case ('AUTHORITATIVE for "is this variant clinically actionable in this disease, and at what tier"') and lists the filter dimensions. It gives clear context for when to reach for this tool, though it doesn't name a specific alternative to use when you want raw evidence instead.

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