Jean — Molecular Biology & Genomics

mask_sequence

Read-only

Mask the parts of a sequence a similarity search should not seed on, using BLAST's own three maskers: DUST for compositionally biased DNA (poly-A, simple repeats), SEG for the protein equivalent, and WindowMasker for repeats that are ordinary in composition but occur far more often than chance allows in the sequences given.

Input Schema

Name	Required	Description	Default
`hicut`	No	SEG's K2, the extension complexity in bits. Only applies when masker is seg.
`level`	No	DUST's T. Higher masks less. Only applies when masker is dust.
`locut`	No	SEG's K1, the trigger complexity in bits. Only applies when masker is seg.
`_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.
`masker`	No	which masker. dust and windowmasker take DNA; seg takes protein. Values: dust (DUST · biased DNA composition), seg (SEG · biased protein composition), windowmasker (WindowMasker · over-represented DNA).	dust
`window`	No	the scored window's width. 0 takes each masker's own default.
`context`	No	WindowMasker only: the other sequences whose statistics define 'over-represented'. Its thresholds come from this SET, so wiring one plasmid asks whether a stretch is unusual for that plasmid, not for the organism. Only applies when masker is windowmasker.
`_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.
`sequence`	No	the sequence to mask. Wire a record or a sequence output, or paste it. Left empty, the open record is used.
`unit_size`	No	WindowMasker's n-mer length. 0 derives it from the length of everything given, the way the tool does. Only applies when masker is windowmasker.

Output Schema

Name	Required	Description
`masked`	Yes	the sequence soft-masked (lower case), which is what BLAST reads as masked
`intervals`	Yes	the masked stretches, 0-based inclusive
`hardMasked`	Yes	the sequence with the masked stretches replaced by N (or X for a protein)
`provenance`	Yes	the masker, the parameters it really used, and for WindowMasker the derived thresholds and the set they came from
`maskedFraction`	Yes	what share of the sequence was masked, 0 to 1. Wire into a $when to refuse a query that is mostly gone

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 safety is covered. The description adds meaningful behavior: what kinds of sequence are masked and how the three algorithms differ. It does not specify hard vs soft masking, but the output schema can carry return details.

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?

It is a single front-loaded sentence with no filler, but it is dense and packs three algorithm definitions into one long clause, which reduces scanability slightly.

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 10 parameters, nested record shapes, full schema coverage, and an output schema, the description establishes the tool's role and masker selection rationale. It leaves operational details such as default open-record behavior and exact return shape to structured fields, which is appropriate.

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 the parameter descriptions already explain masker-specific controls (hicut, locut, level, window, unit_size) and conditional applicability. The description restates the masker-to-use-case mapping but adds no new semantics for individual parameters.

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 ('Mask') and resource ('parts of a sequence a similarity search should not seed on'), and names the three maskers with their biological targets. This distinguishes it from search and alignment siblings without requiring explicit negative routing.

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?

Provides clear context (masking before similarity search) and maps each masker to its use case: DUST for biased DNA, SEG for protein, WindowMasker for over-represented but compositionally ordinary repeats. It does not name a sibling alternative or state when not to use the tool, so it falls short of a 5.

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?