jean — Molecular Biology & Genomics

codon_usage_distance

Read-only

How this region's codon usage compares with the record's OTHER genes (CUFS, Diament, Pinter & Tuller 2014). Every other codon score grades one sequence against a reference TABLE; this one grades two sequences against each other, so it stays available for an organism no authority covers. Answers 'does the gene I inserted use codons like the rest of this construct'.

Input Schema

TableJSON Schema

Name	Required	Description
`_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.
`feature`	No	score this annotated CDS or gene by NAME instead of the selection (the panel's "A CDS / feature…" mode). Its own strand is used unless `reverse` says otherwise.
`reverse`	No	read the region as the reverse complement. Leave unset to take the strand from the annotation when the selection is exactly an annotated CDS or gene, which is what the panel does.
`_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.
`synonymous`	No	normalise each amino acid's codons to sum to 1 (synCUFS), so what remains is the synonymous choice alone. Off compares all 64 codon frequencies, which also reflects amino-acid composition.

Output Schema

TableJSON Schema

Name	Required	Description
`region`	Yes	what was actually scored, naming the STRAND and where it came from — a reverse-strand gene read forwards is a wrong answer, not a missing one
`ceiling`	Yes	the largest distance this run could have produced, for the mode it ran in — read a distance against THIS, never against a constant
`nearest`	Yes	the feature whose codon usage is closest to the scored region
`skipped`	Yes	features that were NOT compared and why — a feature too short for the statistic is reported, never dropped
`compared`	Yes	how many features were compared
`furthest`	Yes	the feature whose codon usage is least like the scored region — the odd one out
`neighbours`	Yes	every other coding feature with its CUFS distance, nearest first — name, span, codons compared and distance
`synonymous`	Yes	whether amino-acid composition was normalised away — the same column of figures means a different thing under each
`strandSource`	Yes	`explicit` (you passed `reverse`), `feature` (taken from the annotation the selection matches) or `default` (forwards, nothing said otherwise)
`nearestDistance`	Yes	its distance. 0 would mean an identical codon distribution; the maximum depends on the mode and is reported as `ceiling` beside it — sqrt(2 ln 2) = 1.177 for the plain form, sqrt(2 ln 2 F) = 5.396 for the synonymous one, which normalises each amino acid separately

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?

The annotations already declare readOnlyHint, destructiveHint false, and openWorldHint false, so safety behavior is covered. The description adds the algorithmic basis (CUFS, Diament et al. 2014) and the key distinction that it grades two sequences against each other rather than one sequence against a reference table, which is useful behavioral 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.

Conciseness5/5

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

The description is three tightly written sentences with no waste. It front-loads the core comparison and then explains the differentiator and use case, so every sentence earns its place.

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, annotations cover safety, and the schema fully documents parameters. The description explains the comparison and its differentiator, though it leaves the prerequisite that the record must contain other genes for the comparison to be meaningful implicit rather than explicit.

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 schema already documents all five parameters in detail. The description does not add parameter-specific meaning beyond the schema's own explanations, which is the expected baseline when the schema does the heavy lifting.

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 comparison: how the region's codon usage compares with the record's OTHER genes, explicitly contrasting this with other codon scores that grade against a reference table. An agent can distinguish it from siblings like codon_optimality or codon_usage_analysis without opening their schemas.

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 gives a clear use case ('does the gene I inserted use codons like the rest of this construct') and contrasts the tool with reference-table-based codon scores, explaining why it remains available for organisms no authority covers. It does not name a specific sibling alternative or an explicit when-not-to-use condition, but the contrast provides strong contextual 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?