jean — Molecular Biology & Genomics

record_composition

Read-only

What the subject record is MADE OF: molecular weight under its own topology and strand count, GC and AT over the resolved bases, and the per-symbol census with the ambiguity codes broken out. The nucleic-acid counterpart of protein_properties, and the same derivation the editor's Properties panel, its inspector and the alignment inspector all draw (Biopython's mass model; ProtParam for a protein subject).

Input Schema

TableJSON Schema

Name	Required	Description
`_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.
`_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.
`doubleStranded`	No	weigh BOTH strands (a plasmid or any dsDNA record) rather than the one strand written in the file (an oligo, an RNA, an alignment row). The two answers differ by about a factor of two, which is why it is a parameter and not a guess. Defaults to true, or false when the record is RNA (U and no T), which is also weighed with RNA residue masses.

Output Schema

TableJSON Schema

Name	Required	Description
`length`	Yes	symbols in the record, non-standard ones included
`strands`	Yes	how many strands the mass was taken over: 2, 1, or 0 for a protein where the question does not arise
`atPercent`	Yes	percent A+T over the same denominator. Null for a protein
`gcPercent`	Yes	percent G+C over the RESOLVED A/C/G/T bases (`standardCount`), which is Biopython's gc_fraction default (ambiguous="remove") — not over the full length, so it complements `atPercent` exactly. Null for a protein
`extinction`	Yes	protein subjects only: e280 under both cystine conventions; null otherwise
`composition`	Yes	one row per standard symbol: code, label, count, and its percent of `standardCount`
`nonStandard`	Yes	the symbols the alphabet does not define — Ns, IUPAC ambiguity codes, gaps — with counts and NO share, because they are excluded from the denominator
`standardCount`	Yes	how many of `length` are standard — the denominator every share here is over
`molecularWeight`	Yes	molecular weight — g/mol for a nucleic acid under `doubleStranded` and the record's own topology, Da for a protein
`isoelectricPoint`	Yes	protein subjects only (ProtParam, Bjellqvist); null otherwise

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A3.9/5.0

Behavior4/5

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 safe, local, non-mutating profile is covered. The description adds genuine context beyond that and the schema by disclosing the derivation sources (Biopython mass model; ProtParam for a protein subject) and tying outputs to the editor's Properties/inspector panels, though it says nothing about error or edge-case behavior.

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?

Two information-dense sentences with the computation front-loaded and no filler; it earns most of its length. It is slightly heavy with enumerations and parenthetical provenance, but nothing is redundant.

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?

An output schema exists, so return values need no prose, and the schema fully documents parameters. Given the nested _subject object and the specific computation, the description supplies enough to call correctly; only explicit alternative routing is absent.

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 the nested _subject and doubleStranded parameters are fully documented in the schema, so the baseline is 3. The description adds only indirect meaning, linking 'topology and strand count' and 'resolved bases' to the computation without new syntax or format detail beyond the schema's own doubleStranded explanation.

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 concrete computation and enumerates its outputs precisely (molecular weight under topology/strand count, GC and AT over resolved bases, per-symbol census with ambiguity codes). It also names the sibling it shadows (protein_properties) and its counterpart role, so an agent can tell what this computes without opening the schema.

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?

Framing it as 'the nucleic-acid counterpart of protein_properties' implies the protein-subject alternative, but it never states an explicit when/when-not, nor how it differs from nearby siblings like gc_content or melting_temperature. Usage is only inferable from the described outputs.

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?