jean — Molecular Biology & Genomics

protein_signal_peptide

Read-only

Signal-peptidase cleavage sites in a protein, by von Heijne's (1986) weight matrix as implemented by EMBOSS sigcleave. Scores a 15-residue window at every position (the 13 residues before the cut plus the first two after) against either the eukaryotic or the prokaryotic training set. Predicts WHERE the cut would fall, not WHETHER the protein is secreted — a high score away from the N-terminus is a look-alike, not a secretion call.

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.
`kingdom`	No	which of von Heijne's training sets to score against: 161 aligned eukaryotic or 36 prokaryotic signal peptides. Pick the one matching the EXPRESSION HOST — the two disagree by several points on the same sequence.	eukaryote
`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.
`minWeight`	No	report sites scoring strictly above this. EMBOSS's default of 3.5 finds ~95% of real signal peptides and rejects ~95% of non-signal sequences.

Output Schema

TableJSON Schema

Name	Required	Description
`score`	Yes	the best site's score — a sum of 15 log-odds, NOT a probability
`sites`	Yes	every site above the threshold, best first: { cleavageAfter, score, start, end, window, maturePeptide }
`matrix`	Yes	which training set was used, and how many peptides it was built from
`scores`	Yes	the score at every position, thresholded or not — the series a plot draws
`siteCount`	Yes	how many sites cleared the threshold
`cleavageAfter`	Yes	1-based residue the best site cuts after; the mature chain starts at the next one. 0 when nothing cleared the threshold
`maturePeptide`	Yes	the predicted mature chain, from the cleavage site to the end
`signalPeptide`	Yes	residues 1..cleavageAfter, the predicted signal peptide

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description goes beyond that by disclosing the algorithm, the exact window (13 residues before the cut plus two after), the training-set distinction, and an important interpretation caveat about false positives — real behavioral context rather than restated annotations.

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?

Three dense sentences, front-loaded with the method and window before the caveat. Every sentence carries information, though the technical density of the middle sentence is slightly heavy for a first read.

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?

With an output schema present the description need not explain return values, and it adequately covers what is computed, how, and how to interpret the scores. Combined with full schema coverage and annotations, an agent has what it needs to invoke this 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%, so the schema already documents kingdom (training-set selection) and minWeight (default 3.5, ~95% sensitivity/specificity). The description echoes the eukaryotic/prokaryotic choice but adds no syntax or semantics beyond what the schema fields already state, so the baseline of 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 verb and resource (signal-peptidase cleavage sites in a protein) and names the exact method (von Heijne 1986 weight matrix via EMBOSS sigcleave). It explicitly scopes what the tool does NOT do — 'predicts WHERE the cut would fall, not WHETHER the protein is secreted' — which cleanly separates it from secretion/membrane siblings like protein_membrane_profile or protein_topology.

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?

Gives clear context for use (scoring a 15-residue window against a eukaryotic or prokaryotic training set) and a strong interpretation caveat that a high score away from the N-terminus is a look-alike, not a secretion call. It stops short of naming an alternative sibling tool for secretion prediction, so no explicit alternatives are offered.

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?