jean — Molecular Biology & Genomics

design_gibson_primers

Read-only

Design the PCR primers that CREATE the terminal homology a Gibson/NEBuilder/In-Fusion assembly needs: a Tm-matched pair per fragment, each carrying the 5' overhang that fuses it to its neighbour in the order given (pydna assembly_fragments). This is the step that turns a planned assembly into oligos you can order.

Input Schema

TableJSON 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.
`overlap`	No	homology shared between two adjacent fragments. pydna splits it across the junction, so each primer's 5' tail is about half this. In bp.
`_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.
`circular`	No	close the ring: the last fragment also overlaps the first.
`fragments`	No	the fragments to join, IN ASSEMBLY ORDER — wire upstream `record` outputs here, or list library document names/ids.
`target_tm`	No	target annealing Tm for each primer's 3' footprint. In °C.
`conditions`	No	salt, magnesium, dNTP and oligo concentrations plus the salt-correction method the target Tm is measured in. Left unset it is filled from your reaction-conditions settings, and falls back to pydna's Taq defaults when there are none. Advanced.
`min_footprint`	No	shortest annealing footprint the designer may settle for (pydna's `limit`). In nt. Advanced.
`include_subject`	No	put the node's subject first, as the backbone.
`synthesis_scale`	No	catalogue product to price the oligos at (an `oligo-list-prices` record id); `auto` prices each at the cheapest product whose published length range covers it. Advanced.	auto

Output Schema

TableJSON Schema

Name	Required	Description
`cost`	Yes	what the oligo set costs at a vendor's published list price: per oligo the product, per-base rate and price, plus the set total, the oligos no listed product covers, and the date the prices were read. One supplier's list price, not a quote
`overlap`	Yes	homology designed between neighbours (bp)
`primers`	Yes	per fragment: the tailed amplicon its primers make, that amplicon's length, and both primers with tail, footprint, length and footprint Tm
`circular`	Yes	whether the ring was closed
`amplicons`	Yes	the PCR products these primers make, as sequence RECORDS carrying each fragment's features at their shifted positions. THIS is what assembles: wire it into `gibson_assemble.fragments`, not the untailed fragments
`costTotal`	Yes	list-price total for the oligos that could be priced (see `cost.unpriced` for any that could not)
`conditions`	Yes	the buffer the target Tm was measured in — salt, magnesium, dNTPs, oligo concentration and the salt-correction method — or a note saying pydna's defaults were used
`primerCount`	Yes	oligos to order (two per fragment)

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A4/5.0

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 safety profile is covered. The description adds genuine behavioral context beyond that: the underlying engine is pydna's assembly_fragments, the output is a matched primer pair per fragment rather than an assembled construct, and each primer's 5' tail is the fusion element — telling the agent this is a design/compute step, not a wet-lab or mutation step.

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?

Two sentences, front-loaded with the action and resource, with the engine citation kept as a short parenthetical and the workflow payoff in the final clause. No filler sentences and nothing repeated from the annotations or schema.

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 complex 10-parameter tool with a fully documented schema and an output schema, the description supplies the workflow framing an agent needs: what the output is, that fragments must be ordered, and which engine is used. Minor gaps remain — it does not mention that all parameters are optional with sensible defaults or how the subject/backbone handling works — but the structured fields cover those.

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%, so the schema already documents overlap, target_tm, circular, conditions and the rest in detail. The description only reinforces fragment ordering and the Tm-matched/overhang concept; it adds little parameter-level meaning the schema does not already carry, so the baseline of 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?

Specific verb (design) plus resource (PCR primers for Gibson/NEBuilder/In-Fusion assembly) and a clear statement of what is produced: a Tm-matched primer pair per fragment with 5' fusion overhangs. The closing line separates it from assembly-simulation steps by framing it as the oligo-ordering step, but it never names a sibling tool (e.g. gibson_assemble, design_fusion_site_primers) explicitly, so differentiation is inferential rather than stated.

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 context of use: after a planned assembly exists, this is the step that converts it into orderable oligos, and fragments must be supplied in assembly order. No exclusions or named alternatives are provided, so an agent must still infer when to prefer this over the generic primer designers or the assembly-simulation siblings.

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?