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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds real behavior beyond that — recomputation semantics, the fact that alpha narrows the heterozygote window and makes calls more liberal, and that error_rate is RE-ESTIMATED from the no-call rate and the actually-used value is reported. It does not mention prerequisites such as the array needing usable genotype confidences or what happens when recomputation fails.

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?

A single sentence with the distinguishing claim front-loaded, which is the right priority for a crowded sibling namespace. The colon-and-em-dash construction makes the second half dense, but no sentence is filler.

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 an output schema present and full schema coverage, the description needn't document return values, and it covers what is computed and how. However, for a tool that can refuse on ambiguous input and depends on array-provided genotype calls, it omits the input preconditions and the 'refuses rather than guessing' behavior, leaving those to the schema alone.

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% and the parameter descriptions are already unusually detailed (APT config names, ranges, re-estimation behavior), so the baseline is 3. The description restates alpha and error_rate in condensed form but contributes no semantics absent from the schema, and says nothing about min_genomic_span.

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 and resource — 'Recompute loss of heterozygosity' — and pins the data source to 'an Affymetrix array's own per-marker genotype calls' rather than producer-written runs. The named algorithm ('APT's window method') further disambiguates it from the surrounding copy_number_* family.

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 'rather than reading the runs the producer wrote' clause gives a clear selection rule: use this when you want LOH re-derived from genotypes instead of trusting vendor calls. It stops short of naming a sibling tool or stating explicit exclusions (e.g. when producer calls are preferable, or that the input must carry genotype calls).

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