jean — Molecular Biology & Genomics

rank_reference_genes

Read-only

Which candidate reference gene is actually stable, ranked by all four published algorithms at once plus the RefFinder consensus: geNorm (pairwise variation M), NormFinder (intra/inter-group variance), BestKeeper (SD of raw Cq and correlation to the index) and the comparative delta-Ct method. They disagree on real plates, which is the point of running them side by side; the consensus is the geometric mean of the four ranks. Also returns geNorm's pairwise variation V(n/n+1), whose 0.15 cutoff is what says HOW MANY genes to normalise to.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`_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.
`cq_table`	Yes	the long-format table: `Target,Sample,Cq`, one row per measurement. A fourth `Group` column is optional and is what unlocks NormFinder's GROUPED arm; without it NormFinder answers a different question and the result says so.
`normfinder_arm`	No	which NormFinder to run. `auto` uses the grouped model when the table has a Group column and the ungrouped one when it does not; `ungrouped` forces the variance-only estimate even on a grouped table. They answer DIFFERENT questions — grouped separates intra- from inter-group variation, ungrouped cannot — so this is a choice, not a fallback. Values: auto (Auto (grouped when the table says so)), ungrouped (Ungrouped (force)). Advanced.	auto

Output Schema

TableJSON Schema

Name	Required	Description
`genormM`	Yes	geNorm's stepwise elimination: the M value of every target at every step
`grouped`	Yes	whether NormFinder ran its grouped arm, and why not when it did not
`ranking`	Yes	the consensus ranking, most stable first, with every algorithm's own rank beside it
`pairwiseV`	Yes	V(n/n+1), the pairwise variation that answers how many reference genes are enough. Below 0.15 an extra gene is not worth it (Vandesompele 2002)
`perMethod`	Yes	each algorithm's own order and 1-based ranks, so a consensus can be read back to the four opinions behind it
`mostStable`	Yes	the consensus winner, named
`recommendedCount`	Yes	the smallest n whose V(n/n+1) falls under 0.15, or 0 when none does. A 0 means this plate does not support the usual answer, not that the run failed

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare a safe read-only operation (readOnlyHint=true, destructiveHint=false, openWorldHint=false), and the description adds that it computes four algorithms plus a consensus and returns geNorm's pairwise variation. It does not disclose operational constraints such as input validation or runtime, but it adds useful computational context beyond the annotations.

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?

The description is front-loaded with purpose and dense with relevant technical detail. The sentences are long and parenthetical, but each conveys distinct algorithm or consensus information, and the length is justified by the tool's complexity.

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

Completeness5/5

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

Given the tool's complexity, the presence of an output schema, complete parameter descriptions, and annotations covering safety, the description supplies the needed domain context about the four algorithms and RefFinder consensus. Nothing required for correct invocation is missing.

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%, so the baseline is 3. The description explains the NormFinder grouped/ungrouped distinction and geNorm pairwise variation conceptually, but these are already covered by the schema's cq_table and normfinder_arm descriptions; it adds no extra syntax or constraint mapping.

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?

The description states a specific verb and resource: ranking candidate reference genes by stability. It names the four published algorithms and the RefFinder consensus, which differentiates it from generic stability or concordance siblings. An agent can tell what this tool does without opening the schema.

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?

It explains the rationale for running all four algorithms side by side and what geNorm's pairwise variation cutoff tells you, giving clear context for when the tool is appropriate. It does not name alternative sibling tools or state when not to use it, so it stops short of explicit routing.

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?