jean — Molecular Biology & Genomics

protein_disorder

Read-only

Intrinsic disorder along a protein by FoldIndex (Prilusky 2005): I_F = 2.785·⟨H⟩ − |⟨R⟩| − 1.151 over a sliding window, where ⟨H⟩ is mean normalized Kyte-Doolittle hydropathy and ⟨R⟩ the mean net charge per residue. Negative means predicted unfolded. Reports the whole-protein score, the per-window series, the runs below zero, and the Uversky charge-hydropathy point with the boundary it was judged against.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`pH`	No	pH for the Henderson-Hasselbalch model, ignored by 'net' (default 7.0, the pH the paper's ⟨R⟩ is defined at). Only applies when chargeModel is henderson-hasselbalch.
`_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.
`pKaSet`	No	named pKa set for the Henderson-Hasselbalch model (default IPC_protein, which is idpr's). Values: EMBOSS (EMBOSS (Rice 2000)), DTASelect (DTASelect (Tabb 2002)), Solomons (Solomons (Solomons 1992)), Sillero (Sillero (Sillero 1989)), Rodwell (Rodwell (Rodwell 1982)), Lehninger (Lehninger (Nelson 2017)), Toseland (Toseland (Toseland 2006)), Thurlkill (Thurlkill (Thurlkill 2006)), Nozaki (Nozaki (Nozaki 1971)), Dawson (Dawson (Dawson 1989)), Bjellqvist (Bjellqvist (Bjellqvist 1994)), ProMoST (ProMoST (Halligan 2004)), IPC_protein (IPC_protein (Kozlowski 2016)), IPC_peptide (IPC_peptide (Kozlowski 2016)), Vollhardt (Vollhardt (Vollhardt 2014)).	IPC_protein
`window`	No	sliding window in residues, odd so a window has a centre residue to report at (default 51, the size the FoldIndex paper uses). Short windows expose single loops; long ones report whole domains.
`protein`	Yes	the protein sequence (unambiguous one-letter codes); wire it from translate_sequence.
`_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.
`chargeModel`	No	'net' counts whole charges K+R−D−E, which is what the paper does; 'henderson-hasselbalch' uses fractional charges at `pH`. They answer different questions and only the first is settled by the paper.	net
`countHistidine`	No	count histidine as positive in the 'net' model. False by default: the paper says charged residues at pH 7.0, and His (pKa ~6) is ~9% protonated there, so Uversky's set is K,R vs D,E — exposed because some FoldIndex descendants do count it.

Output Schema

TableJSON Schema

Name	Required	Description
`plot`	Yes	the FoldIndex profile as a plot; below zero is predicted disordered
`scores`	Yes	just the I_F value per window, parallel to `positions`
`window`	Yes	the window actually used
`overall`	Yes	whole-protein FoldIndex from the global means — the number the 2005 paper's abstract reports. Below zero = predicted unfolded
`windows`	Yes	every window: { position, centerResidue, hydropathy, charge, score } — the series a plot draws
`boundary`	Yes	the Uversky 2000 boundary \|⟨R⟩\| = 2.785·⟨H⟩ − 1.151 evaluated at this protein's ⟨H⟩ — what `meanNetCharge` is above or below
`segments`	Yes	runs of consecutive negative windows as 1-based inclusive residue spans, with each run's mean and minimum I_F
`unfolded`	Yes	whether the whole-protein point sits above that boundary, i.e. predicted natively unfolded
`positions`	Yes	1-based centre residue of each window, parallel to `scores`
`pKaSetName`	Yes	the pKa set actually used, or '' for the 'net' model which needs none
`chargeModel`	Yes	the charge model actually used
`windowCount`	Yes	how many windows were scored — the series length, so a fraction can be read back
`meanNetCharge`	Yes	\|⟨R⟩\| over the whole chain — the y of the Uversky point
`meanHydropathy`	Yes	⟨H⟩ over the whole chain — the x of the Uversky charge-hydropathy point
`disorderedWindows`	Yes	how many windows score below zero
`disorderedFraction`	Yes	that count as a fraction of all windows

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, so the safety profile is covered. The description adds real behavioral context beyond that: the exact scoring model, the meaning of the score sign, and what is reported (whole-protein score, per-window series, sub-zero runs, Uversky CH point). It stops short of noting cost, limits, or edge cases (e.g., short sequences).

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?

Front-loaded with the method name and formula, then the sign interpretation, then the reported outputs. Two dense sentences with little waste; the formula is arguably verbose but is the tool's core definition and earns its place.

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?

For an 8-parameter tool with nested objects, an output schema, and full schema coverage, the description supplies the method, its interpretation, and its outputs, while annotations carry the safety profile. An agent has everything needed to select and call it correctly; only sibling routing is missing, which is scored under usage guidelines.

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 every parameter (pH, pKaSet, window, protein, chargeModel, countHistidine, _subject, _files) is already documented in detail. The description only obliquely touches parameters via 'sliding window' and 'mean net charge per residue', adding essentially nothing beyond the schema, so the baseline 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+resource: predicting intrinsic disorder along a protein via the named FoldIndex method (Prilusky 2005), including the exact formula and the sign interpretation ('negative means predicted unfolded'). This is far more specific than a generic 'analyze protein'. However, it never names or contrasts with the obvious sibling protein_disorder_metapredict, so the differentiation is implicit (method-based) rather than explicit.

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?

Usage is only implied: an agent infers it is for disorder prediction and that negative scores indicate unfolded regions. There is no statement of when to prefer this over protein_disorder_metapredict, protein_profile, or protein_membrane_profile, and no prerequisites or exclusions are given.

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?