Jean — Molecular Biology & Genomics

discover_reference_stability

Read-only

Ask whether the genes used to normalize expression (reference or housekeeping genes, such as GAPDH, ACTB or B2M) are more or less variable across human tissues than genes of the same abundance, on GTEx v8 median expression.

Input Schema

Name	Required	Description	Default
`alpha`	No	false discovery rate at which a candidate is called more variable, or steadier, than its peers.
`genes`	Yes	the candidate reference genes, as current HGNC symbols (GAPD is GAPDH).
`_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.
`tissues`	No	GTEx tissue names to compare across, three or more; empty means all 54.
`_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.
`correction`	No	Benjamini–Hochberg (independent or positively dependent tests) or Benjamini–Yekutieli (any dependence; less power). Values: BH (Benjamini–Hochberg), BY (Benjamini–Yekutieli).	BH
`neighbours`	No	how many genes nearest in mean expression each candidate is ranked among. The smallest p it can give is 1 / (neighbours + 1).
`pseudocount`	No	added to TPM before the logarithm, so a tissue with no expression has one. Advanced.

Output Schema

Name	Required	Description
`result`	Yes	the full result
`stable`	Yes	the candidates steadier than their expression peers at the chosen false discovery rate
`rankers`	Yes	geNorm M, NormFinder, BestKeeper, comparative ΔCt and the RefFinder consensus over the candidates
`unstable`	Yes	the candidates more variable across tissues than their expression peers at the chosen false discovery rate
`candidates`	Yes	every candidate's mean and SD of log2 expression, the expression band of its peers, its percentile among them and both p and q

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint true, openWorldHint false, and destructiveHint false, so the safety profile is covered. The description adds useful context about the GTEx v8 median expression basis and abundance-matched comparison, but it does not disclose the statistical testing/FDR behavior beyond what the schema parameters convey; the output schema covers return values.

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?

A single sentence conveys the question, gene examples, comparison baseline, and dataset. It is appropriately dense and front-loads the central question, though the 'Ask whether...' phrasing is slightly indirect rather than an imperative verb.

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?

Given 100% schema coverage, an output schema, and read-only annotations, the description provides the essential scientific framing: candidate reference genes versus abundance-matched peers on GTEx v8. It could mention the rank_reference_genes relationship or the statistical-test nature, but call-critical details are in structured fields.

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 coverage is 100%, so the schema already defines genes, tissues, alpha, correction, neighbours, pseudocount, _files, and _subject. The description supplies examples such as GAPDH, ACTB, and B2M and reinforces the same-abundance comparison, but adds no parameter-level syntax or constraints beyond the schema. Baseline 3 is appropriate.

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?

The description states a specific analytical question: whether candidate reference/housekeeping genes, with examples, are more or less variable than abundance-matched genes across human tissues on GTEx v8. It is clear what the tool evaluates, though it does not distinguish itself from sibling tools such as rank_reference_genes or discover_reference_concordance.

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

Usage Guidelines2/5

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

It implies the tool is for assessing candidate normalization genes, but gives no explicit when-to-use, when-not-to-use, prerequisites, or alternative tools. An agent must infer whether to call this versus rank_reference_genes or other reference-gene tools.

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?