jean — Molecular Biology & Genomics

copy_number_somatic

Read-only

Read an Affymetrix array result's own somatic-mutation calls: one row per mutation probe set with the producer's call, the score behind it and the two thresholds that call was graded against. OncoScan CNV Plus states this table; CytoScan and SNP 6.0 results do not, and the tool says so rather than answering empty.

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.
`detected_only`	No	report only the calls the producer detected. Default false: the undetected rows are what say the probe set was READ and came back wild type, which is a different answer from the probe set being absent.

Output Schema

TableJSON Schema

Name	Required	Description
`calls`	Yes	one entry per mutation probe set: probe_set (the producer's own identifier), call (its word — `Detected`, `Undetected`, or a third this reader passes through unchanged), detected (that word tested against the undetected one), score (MutScore, the statistic the call was made on), signal (QNSignal, the quantile-normalized signal behind the score), threshold_high and threshold_low (MutThreshHigh/MutThreshLow — the bars THIS probe set was graded at, which differ row to row), and from the array's annotation database for the genome the file states: gene, mutation (protein and cDNA change), cosmic (COSMIC id), chromosome, and position (1-based, the variant's first base); all five are null for a probe set that database does not list or when the file states no genome it is cached for.
`summary`	Yes	how many mutation probe sets this file states, how many the producer detected, and which array wrote them
`detected`	Yes	the subset of `calls` whose word is not the undetected one — the mutations this sample actually carries, in the same shape
`provenance`	Yes	which file answered, the container kind it was read from, the name of the data set the somatic table was found in, how many rows it holds, placement (which annotation database, genome and retrieval date placed the calls and how many it placed, or why none were placed), and the vocabulary note: the call words are the producer's own and are not normalized here

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations already establish the safe read-only, non-destructive, closed-world profile, and the description adds substantive behavior on top: the table exists only for OncoScan CNV Plus, and the tool reports that explicitly instead of returning an empty result. That failure-mode disclosure is exactly the kind of context annotations cannot carry.

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

Conciseness5/5

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

Two sentences with zero filler: the first front-loads what the tool returns, the second carries the platform gate and the refusal behavior. Every clause adds information an agent needs.

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?

With annotations covering safety and an output schema covering return shape, the description only needs to add scope and caveats, which it does well (platform availability, explicit refusal instead of empty). The remaining gap is the absence of any pointer to the sibling tool an agent should use when the platform is CytoScan or SNP 6.0.

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% and the parameters (file, _files, _subject, detected_only) are each documented in the schema, including the detected_only default semantics. The description adds no per-parameter detail and never mentions detected_only, so the schema does the heavy lifting and the baseline of 3 applies.

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

Purpose4/5

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

States a specific verb and resource: reading an Affymetrix array result's own somatic-mutation calls, with a precise row-level description (probe set, call, score, two thresholds). It does not explicitly name or contrast itself with the many copy_number_* siblings (e.g. copy_number_read, copy_number_findings), so differentiation is by subject matter rather than by direct sibling comparison.

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

Usage Guidelines4/5

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

Gives a clear when-to-use context (you want the producer's own somatic calls from an Affymetrix array) plus a when-not condition: only OncoScan CNV Plus states this table, and CytoScan/SNP 6.0 results will not have it. It stops short of naming an alternative tool to use for those other platforms, so the routing guidance is incomplete.

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?