jean — Molecular Biology & Genomics

protein_disorder_metapredict

Read-only

Per-residue intrinsic disorder by metapredict (Emenecker, Griffith & Holehouse, Biophys J 2021; V2/V3 the lab's successors), a bidirectional LSTM trained to reproduce a consensus of disorder predictors, run locally. Reports a 0–1 score per residue, the IDRs and folded domains its domain caller draws from the smoothed profile, and the percentage of residues at or above the network's threshold. A different question from protein_disorder's FoldIndex, which reads composition alone.

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.
`convert`	No	read B as N, U as C, X as G and Z as Q, as metapredict's FASTA readers do; off refuses them. Default true. Advanced.
`protein`	Yes	the protein sequence; wire it from translate_sequence.
`version`	No	which trained network: V3 (the package default), V2, or V1 (the published 2021 network). Values: V3 (V3 (default)), V2 (V2), V1 (V1 (published, legacy)).	V3
`_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.
`threshold`	No	smoothed score above which a residue can seed an IDR, and per-residue score at or above which it counts as disordered. Omit for the network's own: V1 0.42, V2 and V3 0.5.
`gapClosure`	No	the longest run of sub-threshold residues closed when flanked by disordered runs of the same length. Default 10. Advanced.
`minimumIdrSize`	No	the shortest IDR the domain caller reports, in residues; also sets the smoothing window (twice this, made odd). Default 12. Advanced.
`minimumFoldedDomain`	No	gaps between IDRs shorter than this are re-tested at 0.75× the threshold, so short ordered stretches inside an IDR are absorbed. Default 50. Advanced.

Output Schema

TableJSON Schema

Name	Required	Description
`idrs`	Yes	intrinsically disordered regions as 1-based inclusive spans with their length and mean score
`scores`	Yes	the per-residue disorder score, 0–1, residue 1 first
`version`	Yes	the network actually used
`converted`	Yes	how many B/U/X/Z residues were read as N/C/G/Q
`threshold`	Yes	the threshold actually used
`idrResidues`	Yes	how many residues the IDRs cover
`foldedDomains`	Yes	the complementary folded domains, same shape
`percentDisordered`	Yes	percentage of residues scoring at or above the threshold, to 3 dp
`disorderedResidues`	Yes	how many residues score at or above the threshold

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already establish readOnlyHint, destructiveHint=false, and openWorldHint=false, so safety behavior is covered. The description adds useful context beyond that: local execution, the LSTM/consensus methodology, output scoring per residue, IDR/folded-domain caller behavior, and threshold usage.

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?

Three dense sentences: method and scope first, reported outputs second, sibling differentiation last. No filler, and the most important routing information is front-loaded.

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 a complex, 9-parameter tool with an output schema and rich annotations, the description supplies the high-level purpose, method, outputs, and sibling distinction. The schema and output schema carry parameter and return details, so nothing essential is missing for correct tool selection or invocation.

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%, and every parameter is already documented in the schema. The description mentions the network threshold conceptually but does not add meaning for specific parameters such as version, gapClosure, minimumIdrSize, or minimumFoldedDomain, so the baseline 3 applies.

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?

States a specific computation (per-residue intrinsic disorder by metapredict) and names the underlying method, model class, and outputs. It also explicitly distinguishes itself from the sibling protein_disorder, so an agent can tell the two apart without opening either 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?

Names the alternative protein_disorder/FoldIndex and clarifies that it answers a different question based on composition alone. This gives clear selection context, though it stops short of explicit when-to-use/when-not phrasing.

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?