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

Annotations already cover readOnlyHint and non-destructiveness, so the bar is lower, but the description adds real interpretive context: that 'a ranker always finds a most stable gene' so only the null tells you if a candidate is actually stable, and that tissue medians hide within-tissue inter-individual variation. These are genuine behavioral caveats not present in the structured fields.

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 core question is front-loaded and almost every clause carries information. It is a single dense block with very long sentences, and it contains a small internal slip ('four rankers' followed by a list of five), which slightly undercuts readability.

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 an 8-parameter, nested-schema, output-schema-bearing tool, the description supplies the statistical model, the null/ranker distinction, and the tissue-vs-sample limitation. With an output schema present it need not explain return values, and the remaining gap (which sibling to use for pure ranking) is minor.

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 description earns an extra point by giving semantics the schema does not, such as the 1,000-neighbour default, the 19,107 protein-coding background, the FDR correction applying across candidates, and the smallest attainable p (1/(neighbours+1)). It stops short of mapping these to individual named parameters.

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 states a precise, testable question: whether reference/housekeeping genes (GAPDH, ACTB, B2M) are more or less variable across tissues than abundance-matched peers on GTEx v8. This is a specific verb+resource that an agent can distinguish from the neighboring rank_reference_genes and discover_reference_concordance tools. The statistical framing (p for 'more variable' vs 'steadier') pins down exactly what is being asked.

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?

It gives an explicit scope exclusion — 'this answers across tissues, not across samples of one tissue' — and explains when the null hypothesis matters versus the rankers. However, it never names the sibling tools (e.g. rank_reference_genes) or says which alternative to pick, so routing is left partly to inference.

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