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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered; the description's added value is methodological, explaining what is fitted and how K is scored by held-out-genotype cross-entropy. It does not disclose the practical cost of fitting every K in the range (up to 20 alternating NMF runs on a whole VCF), nor does it warn about runtime or memory, which are the main behavioral risks for this tool.

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?

One dense but well-structured sentence: resource first, then method, then K-selection criterion, then citation. It is appropriately short for a tool whose parameters are fully documented elsewhere, though the stacked jargon (sparse non-negative matrix factorisation, cross-entropy) makes it slightly harder to scan than a plainer phrasing would.

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 14-parameter tool with nested objects and an output schema, the description correctly leaves return values to the schema but omits the usage context an agent needs to pick it (versus population_fst or genotype_pca) and says nothing about the sample-table input that drives groupBy/populations. It is adequate as a definition of the computation but thin as a decision aid.

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 the schema already documents all 14 parameters including kFrom/kTo, holdOut, alpha and seed with meaningful explanations. The description adds no parameter-level detail beyond the schema (it mentions 'K in a range' and held-out scoring, which the schema already captures), so the 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?

The description names a specific computation ('individual ancestry coefficients, the ADMIXTURE-style picture') and pins the method (LEA snmf, sparse NMF, cross-entropy over K). It is clear this is a population-structure/ancestry estimation tool, distinct in substance from siblings like population_fst or genotype_pca, though it never names those alternatives explicitly.

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?

There is no when-to-use guidance at all: nothing says when ancestry-coefficient estimation is the right choice versus population_fst, population_site_stats, genotype_pca, or linkage_disequilibrium. No prerequisites are stated (a VCF is required, and the populations/groupBy relationship is left entirely to the schema), and there are no exclusions or caveats about input size or ploidy assumptions.

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