jean — Molecular Biology & Genomics

protein_properties

Read-only

Molecular weight (average + monoisotopic), molecular formula, isoelectric point, instability index and amphipathicity (Boman index, Eisenberg hydrophobic moment) of a protein sequence (Biopython ProtParam + peptides + pyteomics).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`pH`	No	pH the net charge is reported at (default 7.0).
`_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.
`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.
`gravyScale`	No	hydropathy scale GRAVY is averaged over (all 28 ProtParam/ProtScale scales; default Kyte & Doolittle). Values: KyteDoolitle (Kyte & Doolittle (1982)), Aboderin (Aboderin (Int J Biochem 2:537)), AbrahamLeo (Abraham & Leo (1987)), Argos (Argos (Eur J Biochem 128:565)), BlackMould (Black & Mould (1991)), BullBreese (Bull & Breese (1974)), Casari (Casari & Sippl, hydrophobic potential (JMB 224:725)), Cid (Cid (Protein Eng 5:373)), Cowan3.4 (Cowan at pH 3.4 (1990)), Cowan7.5 (Cowan at pH 7.5 (1990)), Eisenberg (Eisenberg, normalized consensus (1984)), Engelman (Engelman, transfer free energy (Annu Rev Biophys 15:321)), Fasman (Fasman (1989)), Fauchere (Fauchere (1983)), GoldSack (Goldsack & Chalifoux, free energy of mixing (J Theor Biol 39:645)), Guy (Guy, transfer free energy kcal/mol (1985)), Jones (Jones (J Theor Biol 50:167)), Juretic (Juretic (Theor Comput Chem 5:405)), Kidera (Kidera factors (J Protein Chem 4:23)), Miyazawa (Miyazawa, contact energy from 3D structures (1985)), Parker (Parker, HYDROPHILICITY from HPLC retention (1986)), Ponnuswamy (Ponnuswamy, folded-protein character (Prog Biophys Mol Biol 59:57)), Rose (Rose (1985)), Roseman (Roseman (1988)), Sweet (Sweet, optimized matching OMH (1983)), Tanford (Tanford (1962)), Wilson (Wilson, hydrophobic constants from HPLC retention (1981)), Zimmerman (Zimmerman (J Theor Biol 21:170)).	KyteDoolitle
`momentWindow`	No	sliding window for the hydrophobic moment, in residues (default 11; clamped to the sequence length).
`cystineConvention`	No	how the oxidised e280 counts cysteines: 'cystine' = 125 per disulfide (ProtParam, default) or 'perCysteine' = 62.5 per residue (SnapGene). They differ only on an ODD cysteine count.	cystine

Output Schema

TableJSON Schema

Name	Required	Description
`mw`	Yes	molecular weight [Da]
`pI`	Yes	isoelectric point
`a280`	Yes	A280 of a 1 g/L solution (cystines form) — divide a spectrophotometer reading by this
`turn`	Yes	fraction of residues favouring a turn
`atoms`	Yes	total number of atoms in the molecule
`boman`	Yes	Boman potential protein-interaction index [kcal/mol] (>2.48 = protein-binding)
`gravy`	Yes	grand average of hydropathicity over `gravyScale`
`helix`	Yes	fraction of residues favouring an alpha-helix
`sheet`	Yes	fraction of residues favouring a beta-sheet
`charge`	Yes	net charge at `pH`
`formula`	Yes	molecular formula, ProtParam style (e.g. C1755H2634N466O557S5)
`elements`	Yes	atom counts per element (C, H, N, O, S) behind the formula
`aliphatic`	Yes	aliphatic index (Ikai 1980) — higher suggests greater thermostability
`nTerminal`	Yes	the N-terminal residue the N-end rule half-lives below are read from
`gravyScale`	Yes	which hydropathy scale `gravy` was averaged over
`aromaticity`	Yes	aromaticity (Lobry 1994): the F+W+Y frequency, as a fraction
`composition`	Yes	residue counts, one entry per standard amino acid (ProtParam's composition table)
`instability`	Yes	instability index (>40 = unstable in vivo)
`momentHelix`	Yes	max Eisenberg hydrophobic moment at the α-helix periodicity (100°)
`momentSheet`	Yes	max Eisenberg hydrophobic moment at the β-sheet periodicity (160°)
`halfLifeEcoli`	Yes	estimated in-vivo half-life, E. coli (N-end rule)
`halfLifeYeast`	Yes	estimated in-vivo half-life, yeast (N-end rule)
`monoisotopicMw`	Yes	monoisotopic molecular weight [Da] — what mass spectrometry reports
`extinctionReduced`	Yes	molar extinction coefficient at 280 nm [M-1 cm-1], all cysteines reduced
`halfLifeMammalian`	Yes	estimated in-vivo half-life, mammalian reticulocytes (N-end rule); '—' when the N-terminus has no entry
`compositionPercent`	Yes	the same table as mole percent of the chain
`extinctionCystines`	Yes	molar extinction coefficient at 280 nm [M-1 cm-1], cystines formed (per `cystineConvention`)
`gravyHydrophobicEnd`	Yes	which end of `gravyScale` is the hydrophobic one: 'higher' (Kyte & Doolittle and most others) or 'lower' (a transfer free energy or a hydrophilicity scale). Read `gravy` against this, never against zero alone
`gravyZeroIsMeaningful`	Yes	whether `gravyScale` takes both signs. False on the eight one-sided tables (Rose, Miyazawa, Argos, …), where the sign of `gravy` is a property of the scale and says nothing about this protein

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, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds the implementation libraries (Biopython ProtParam, peptides, pyteomics), but does not disclose compute cost, handling of invalid sequences, or any other behavioral trait beyond what the annotations and schema already provide.

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 front-loads the main computed property and remains dense but compact. The parenthetical implementation list is slightly expendable, but there is no wasted framing or repetition.

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 the rich schema, output schema, and annotations, the description supplies the essential purpose and output scope. It does not address sibling routing or nested _subject/_files usage, but those are covered by the schema, so the agent has enough to call the tool correctly.

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%, including detailed enum documentation for gravyScale and cystineConvention. The description adds no parameter-level meaning beyond what the schema already states, so 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?

The description names the resource (a protein sequence) and enumerates the specific computed properties: molecular weight, formula, isoelectric point, instability index, and amphipathicity metrics. This is far more concrete than a tautology, but it is a noun phrase without an action verb and does not explicitly differentiate from siblings like peptide_mass or protein_profile.

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?

There is no guidance on when to use this tool versus alternatives, no exclusions, and no prerequisites. The agent must infer its role from the property list alone.

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?