jean — Molecular Biology & Genomics

copy_number_allele_split

Read-only

Read an Affymetrix array result's own allele-specific copy number: for each segment the major and minor allele counts (1+1, 2+0, 0+0), what they mean (balanced, allelic imbalance, loss of heterozygosity placed against the sample's own ploidy, homozygous deletion), and ASCAT's whole-genome summary over them (LOH fraction, homozygous deletions, modal allele state, whole-genome doubling, genomic instability). OncoScan results state a split when the aberrant-cell fraction was determined; the tool says why when a file states none.

Input Schema

TableJSON Schema

Name	Required	Description
`file`	No	which copy-number file in this project, by name. Unset, it is the project's only one, and it refuses rather than guessing when there are several.
`_files`	No	The project: record references shaped like _subject. Their records become library documents a tool names in sequences/parts/document; a trace or alignment is found by file name.
`_subject`	No	The record to act on: exactly one of sequence, accession (+source), sample (an id from list_samples) or file ({name, text} or {name, base64}); record_index picks one record of several.
`estimated_only`	No	report only the segments the producer split. Default false: an unestimated segment is listed as such, which is a different answer from its absence.

Output Schema

TableJSON Schema

Name	Required	Description
`metrics`	Yes	ASCAT 3.2.0's ascat.metrics() profile columns over the estimated segments, unrounded: n_segs, segs_size, size_odd_segments, size_intermediate_segments, homdel_segs, homdel_largest, homdel_size, homdel_fraction, LOH (autosomal fraction), mode_minA, mode_majA, WGD (0, 1, '1+' or null) and GI (null when WGD is). Null when nothing is estimated
`summary`	Yes	how many segments carry a split, how many are LOH (and copy-neutral), homozygous deletions, imbalanced and balanced, and the autosomal LOH fraction
`segments`	Yes	one entry per segment: chromosome (the file's own name, X not 24), start and end (the file's coordinates), markers, estimated, major and minor (null where not estimated), raw_a and raw_b (the producer's raw nA/nB, null where empty), total_cn (the producer's total, fractional where it made no integer call), state (not-estimated, homozygous-deletion, loh, balanced, imbalanced) and relative_to_ploidy (below, equal, above, for LOH only, null when no ploidy is stated)
`provenance`	Yes	which file answered, the data set the split was read from, how many segments it holds and how many are estimated, and the producer's own fit: ploidy and aberrant-cell fraction as the chip summary states them

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations only declare it as a safe read (readOnlyHint=true, destructiveHint=false, openWorldHint=false), yet the description goes further: it enumerates the allele states it reports (1+1, 2+0, 0+0) with their interpretations and notes that the tool explains why no split is stated when a file reports none. That last point is a genuine behavioral trait beyond the annotations, though return formatting and pagination are left to the output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with what is read before the edge-case behavior about missing splits. The first sentence is long and stacks several parenthetical glosses, but every clause defines a distinct reported quantity rather than padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so the description need not explain return values, yet it still names the key outputs; annotations cover the safety profile. The remaining gap is routing guidance against the other copy_number_* siblings, which the description never addresses.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: the file fallback rule, the _files/_subject project record, and the estimated_only semantics are all documented in the schema itself. The description adds contextual framing (ploidy-relative interpretation, 'estimated' splits) but no parameter syntax or constraints beyond what the schema provides, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb and resource: reading an Affymetrix array result's allele-specific copy number, with major/minor allele counts and the ASCAT whole-genome summary spelled out. That granularity (allele split, LOH fraction, whole-genome doubling) is specific enough to separate it from copy_number_loh, copy_number_segment and copy_number_regions, which cover different slices of copy-number data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Context is implied rather than stated: the tool is for Affymetrix/OncoScan array results and for callers who need the allele-specific split rather than a generic copy-number read. There is no explicit when-to-use versus copy_number_loh or copy_number_segment, and no stated prerequisites, so the agent must infer the selection.

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

All jean — Molecular Biology & Genomics tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?