jean — Molecular Biology & Genomics

design_degenerate_primers

Design degenerate primers from a multiple-sequence ALIGNMENT - the 'amplify every homologue in this family' question, which a single-template designer cannot answer because it only ever sees one sequence. A faithful port of DegePrime (Hugerth et al. 2014). Wire an upstream align_sequences rows output straight in, or paste an aligned FASTA.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`seed`	No	seed for WRM's draw, so a run is REPRODUCIBLE. Upstream is unseeded, so the same alignment can give two answers; a design you cannot reproduce is not one you can order from. Only applies when algorithm is wrm. Advanced.
`skip`	No	bases excluded at each end of every sequence (`-skip`). In nt. Advanced.
`limit`	No	how many pairs to return, best coverage first. Advanced.
`_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.
`length`	No	oligomer length (DegePrime `-l`). In nt.
`_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.
`algorithm`	No	which search picks each window's oligo. `wrm` is DegePrime's own default and is randomised (hence `seed`); `exhaustive` is an exact branch-and-bound that GRADES the heuristics rather than letting them grade each other, and REFUSES a window too large to solve rather than guessing - the problem is NP-hard.	wrm
`alignment`	No	the ALIGNED rows to scan, each `{ name, sequence }` with gaps preserved - wire an upstream `align_sequences` rows output here. Gaps carry information the scan reads, so an unaligned set is not a substitute.
`min_depth`	No	fewest gapless sequences a window needs before it is reported at all (`-depth`). Advanced.
`iterations`	No	WRM restarts (`-iter`). Only applies when algorithm is wrm. Advanced.
`max_product`	No	longest product, in TRIMMED alignment columns. In col.
`min_product`	No	shortest product, in TRIMMED alignment columns. In col.
`trim_cutoff`	No	columns occupied by less than this fraction of sequences are dropped before scanning. Trimming renumbers the alignment, which is why `keptColumns` comes back with the result. Advanced.
`max_degeneracy`	No	degeneracy ceiling (`-d`) - how many distinct oligos the IUPAC code is allowed to stand for. Coerced DOWN when no combination of positions can multiply to it, and the run says so.
`alignment_fasta`	No	an aligned FASTA to scan, when there is no upstream alignment to wire. Sequences must already BE aligned - equal length, gaps as `-`.
`exhaustive_mer_limit`	No	largest number of distinct mers `exhaustive` will attempt before refusing a window. Only applies when algorithm is exhaustive. Advanced.
`min_fraction_matching`	No	a window must bind at least this fraction of the spanning sequences to be a candidate - the coverage floor, and the number that decides whether 'every homologue' is true.

Output Schema

TableJSON Schema

Name	Required	Description
`pairs`	Yes	the primer pairs, best coverage first: both oligos in IUPAC letters, their degeneracy, the fraction of the family each binds, and the product span in trimmed columns
`forward`	Yes	the best pair's forward oligo, IUPAC. Empty when no pair satisfied the constraints
`reverse`	Yes	the best pair's reverse oligo AS ORDERED (reverse-complemented). Empty when no pair satisfied the constraints
`windows`	Yes	every scanned window with its degeneracy, entropy and coverage - the scan behind the pairs
`pairCount`	Yes	how many pairs were found
`keptColumns`	Yes	which columns of the ORIGINAL alignment survived trimming - trimmed column 40 is not alignment column 40, and this is the map back
`degeneracyCoerced`	Yes	true when the ceiling was lowered, so a run never silently answers a different question than it was asked
`maxDegeneracyUsed`	Yes	the degeneracy ceiling actually applied - LOWER than asked when no combination of IUPAC positions can multiply to the request

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds meaningful context beyond them: it identifies the tool as a faithful DegePrime port and stresses that gaps carry information the scan reads, which signals behavioral expectations. It does not restate what the schema already says about refusal/coercion behavior, but it adds real domain framing.

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 sentences, front-loaded with the core purpose and the differentiator before the provenance note. The parenthetical about single-template designers is slightly expansive but earns its place by reinforcing the routing decision. No filler.

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?

An output schema exists, so return values need not be described. With 17 parameters at 100% schema coverage, the description only needs to convey purpose, input modes, and the alignment requirement, all of which it does. Nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds value beyond the schema by specifying that the alignment input accepts an upstream align_sequences `rows` output directly, clarifying the shape and provenance of the alignment/alignment_fasta 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+resource ('Design degenerate primers from a multiple-sequence ALIGNMENT') and immediately frames the distinguishing use case: amplifying every homologue in a family. This separates it from single-template siblings like design_primers and design_primer_pairs without the agent needing to open a 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?

Clearly states when this tool applies (multi-template family amplification) versus when a single-template designer suffices, and tells the agent how to feed it ('wire an upstream align_sequences rows output straight in, or paste an aligned FASTA'). The alternative is described by class rather than named as a specific sibling tool, so it falls just short of fully explicit routing.

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?