jean — Molecular Biology & Genomics

design_codehop

Design CODEHOP hybrid oligos from a block of aligned PROTEIN - for homologues too diverged for nucleotide-level design to see at all. Each primer is a 3' DEGENERATE core over a few conserved residues fused to a 5' non-degenerate consensus clamp, back-translated through a codon-usage table. A different algorithm from the degenerate designer, not a variant of it.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`table`	Yes	the codon-usage table to back-translate the clamp through, BY NAME as the Codon Usage panel lists it. REQUIRED and deliberately without a default: a CODEHOP designed under the wrong organism's usage is wrong in a way nothing downstream can detect, so picking one here would silently pick a host (§1).
`_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.
`strand`	No	which strand to design on. `both` returns forward and reverse sets, which is what a PCR needs.	both
`max_run`	No	longest single-base run allowed; 2003's stated polynucleotide run limit. A primer exceeding it is rejected. In nt. Advanced.
`_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.
`clamp_tm`	No	target melting temperature for the non-degenerate 5' clamp (Rose 2003 step 8: "the current default is 60 °C, which usually provides a clamp of ~20 nucleotides"), measured as nearest-neighbour Tm in the buffer `conditions` names. In °C.
`alignment`	No	the ALIGNED PROTEIN rows, each { name, sequence } in one-letter amino acids with gaps preserved - wire an upstream protein alignment here. At least 3 sequences: the clamp is a CONSENSUS, and two have none worth the name.
`weighting`	No	how the alignment's rows are weighted before the core's consensus is read. Values: pb (Position-based (Henikoff & Henikoff 1994)), none (None — every row counts once). Advanced.	pb
`conditions`	No	salt, magnesium, dNTP and oligo concentrations plus the salt-correction method and any additives the clamp Tm is measured in. Left unset it is filled from your reaction-conditions settings, and falls back to pydna's Taq defaults (SantaLucia & Hicks 2004 table, 250 nM primer, Owczarzy 2008 salt correction) when there are none. Advanced.
`base_cutoff`	No	minimum predicted probability for a base to enter the degenerate core. Advanced.
`block_index`	No	which gapless block to design in, 0-based, ordered as `gaplessBlocks` returns them (blocks of at least 8 ungapped columns). Unset = the first.
`core_lengths`	No	core lengths the scan tries, in residues — every length here is scanned and the best-scoring core kept. Advanced.
`alignment_fasta`	No	an aligned PROTEIN FASTA, when there is no upstream alignment to wire.
`genetic_code_id`	No	NCBI `transl_table` id for the codon-to-residue map. Advanced.
`max_clamp_length`	No	ceiling on clamp growth, so an unreachable Tm REFUSES instead of consuming the whole block. Ours, and a stop condition rather than a published criterion - 40 nt is already twice the ~20 the paper expects. In nt. Advanced.
`max_core_degeneracy`	No	degeneracy ceiling for the 3' core (Rose 2003 step 7: "a maximum degeneracy of 128").

Output Schema

TableJSON Schema

Name	Required	Description
`table`	Yes	which codon table the clamp was back-translated through, named so a design is never unattributable
`forward`	Yes	the first forward oligo, clamp + core
`primers`	Yes	the designed oligos: each with its degenerate 3' core, its consensus 5' clamp, the residues it covers and its degeneracy
`reverse`	Yes	the first reverse oligo
`blockCount`	Yes	how many gapless blocks the alignment offers, so a caller can see there were others to choose
`rejections`	Yes	why each candidate position was rejected - degeneracy, run length, or a clamp that could not reach the Tm
`primerCount`	Yes	how many oligos were designed

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 already declare the safety profile (destructiveHint=false, readOnlyHint=false, openWorldHint=false) and an output schema exists, so the bar is lower. The description still earns credit by disclosing the algorithmic behavior — hybrid degenerate-core/non-degenerate-clamp architecture and codon-usage back-translation — which tells the agent what kind of artifact it will get and why the design differs from a plain degenerate primer.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each load-bearing: purpose first, mechanism second, sibling differentiation last. No filler, no restatement of the name or title, and the rationale ('too diverged for nucleotide-level design') is front-loaded ahead of the mechanics.

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?

For a 16-parameter tool with nested objects, an output schema and full schema description coverage, the description covers purpose, mechanism, and tool selection adequately; return values and parameter details are carried by structured fields. The only thing an agent might want stated upfront — the minimum of three aligned sequences and the mandatory codon table — lives in the schema rather than the prose.

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 meaning beyond the schema by supplying the conceptual model — 'degenerate core' and 'non-degenerate consensus clamp' back-translated through a codon-usage table — which is exactly the frame needed to interpret clamp_tm, core_lengths, max_core_degeneracy, base_cutoff and max_clamp_length correctly.

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?

Specific verb + resource ('Design CODEHOP hybrid oligos from a block of aligned PROTEIN') with the molecular mechanism spelled out (3' degenerate core + 5' consensus clamp, back-translated through a codon-usage table). It explicitly distinguishes itself from the sibling design_degenerate_primers: 'A different algorithm from the degenerate designer, not a variant of it.'

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 a clear selecting condition — 'for homologues too diverged for nucleotide-level design to see at all' — which routes the agent away from nucleotide-level designers and toward this tool. It stops short of naming the specific sibling tool (design_degenerate_primers) or stating explicit exclusions, so it is clear context rather than fully explicit when/when-not 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?