Jean by Melad Labs

antibody_position_frequencies

Read-only

How common each residue of an antibody variable domain is at its IMGT position, and which residues are rarer there than a cut (abYsis's 1% "unusual residue" by default).

Input 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.
`protein`	Yes	the protein sequence (one-letter amino acids); every antibody and T-cell-receptor variable domain in it is read.
`species`	No	species whose HMMs are preferred when numbering (ANARCI's default: human and mouse).
`_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.
`rare_below`	No	a residue is rare where its share of the alleles or sequences is below this fraction (abYsis's unusual-residue cut is 0.01).
`distribution`	No	what each position is counted over: `germline` (IMGT's V and J alleles of `germline_species`) or `repertoire` (the bundled human OAS subset of expressed sequences).	germline
`germline_species`	No	the species whose IMGT germline alleles each position is counted over (germline distribution only; the repertoire is human).	human

Output Schema

Name	Required	Description	Default
`rare`	Yes	one `IMGT position residue (count of n)` string per rare residue, in sequence order
`domains`	Yes	per domain: chain type, span, what the table counted (germline allele counts, or the repertoire's sequence count and subset), and per residue its IMGT position, 0-based sequence index, count, denominator, frequency, the commonest residue there and whether it is rare

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 21, 2026

addedInput schema / properties / distribution

Added value: +{
+  "default": "germline",
+  "description": "what each position is counted over: `germline` (IMGT's V and J alleles of `germline_species`) or `repertoire` (the bundled human OAS subset of expressed sequences).",
+  "enum": [
+    "germline",
+    "repertoire"
+  ],
+  "type": "string"
+}

changedInput schema / properties / germline_species / description

Previous value: -"the species whose IMGT germline alleles each position is counted over."New value: +"the species whose IMGT germline alleles each position is counted over (germline distribution only; the repertoire is human)."

changedInput schema / properties / rare_below / description

Previous value: -"a residue is rare where its share of the alleles is below this fraction (abYsis's unusual-residue cut is 0.01)."New value: +"a residue is rare where its share of the alleles or sequences is below this fraction (abYsis's unusual-residue cut is 0.01)."

changedOutput schema / properties / domains / description

Previous value: -"per domain: chain type, span, the germline table's allele counts, and per residue its IMGT position, 0-based sequence index, allele count, denominator, frequency, the commonest residue there and whether it is rare"New value: +"per domain: chain type, span, what the table counted (germline allele counts, or the repertoire's sequence count and subset), and per residue its IMGT position, 0-based sequence index, count, denominator, frequency, the commonest residue there and whether it is rare"

AddedOct 21, 2026

TDQS

B3.4/5.0

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 covered. The description adds useful behavioural context by naming the abYsis 1% unusual-residue convention and its default, but says nothing about what happens when no variable domain is detected or how the two outputs relate.

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 dense sentence with the core concept front-loaded and no filler. It is efficient, though the parenthetical default could have been dropped since rare_below already carries it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 7 parameters, nested _subject/_files objects and an output schema, the description only needs to frame purpose and the key convention, which it does. It leaves the germline-vs-repertoire choice and the multi-domain case unmentioned, so it is adequate rather than complete.

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 coverage is 100%, so every parameter including distribution, germline_species and rare_below is already documented in the schema. The description only reinforces the default cut value (1%), adding little meaning beyond what the schema supplies; 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 computation: per-residue frequency at IMGT positions of an antibody variable domain, plus which residues fall below a rarity cut. That is concrete enough to separate it from number_antibody, antibody_liabilities and antibody_canonical_classes, though it never names those siblings explicitly.

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?

The intended use case (spotting unusual residues at IMGT positions, abYsis-style) is implied by the wording, but there is no explicit when-to-use, no prerequisite such as needing a numbered variable domain, and no routing to or away from neighbouring antibody tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Jean by Melad Labs 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?