audit_import_quality

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

With no annotations provided, the description carries the full behavioral burden and meets it: it explicitly states the tool is read-only and never modifies Gigwa, writes one CSV row per run under output_dir, returns a worst-first ranked summary, and explains the sampling/pagination behavior. It also discloses that thresholds reflect diagnostic logic rather than arbitrary cutoffs.

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 is long but densely informative and well-structured, with a clear front-loaded purpose, bulleted flag categories, and explicit side effects. Some details are repeated in the schema, but most sentences add decision-relevant context, so the length is earned.

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?

Given the tool's complexity, the description covers purpose, scope, cost behavior, diagnostic criteria, output location, return summary, and read-only safety. The output schema likely covers return structure, and parameter descriptions cover edge cases like the variant_set_db_id warning, so nothing essential 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 coverage is 100%, so the baseline is 3, but the description adds real parameter meaning beyond the schema: it explains how variant_set_db_id scopes the audit, warns never to assemble it by hand because a wrong guess yields an opaque HTTP 500, and ties max_markers/max_samples to the bounded-cost sample. This extra context justifies a score above baseline.

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 a specific verb and resource: 'Scan a Gigwa instance for databases imported with genotype-encoding artifacts.' It clearly distinguishes itself from sibling QC tools by focusing on import failure modes and defining two signal levels, BROKEN and SUSPECT, so an agent can tell it apart from tools like qc_call_rate or diversity_summary.

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 description gives explicit scoping guidance: with no variant_set_db_id it audits every run on the instance, and passing one audits a single variant set. It also explains when it is safe to use across a production instance because sampling is bounded and constant-cost, making the usage context concrete.

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