Jean — Molecular Biology & Genomics

design_lamp_primers

Design LAMP (loop-mediated isothermal amplification) primer SETS - four core oligos (F3 · B3 · FIP · BIP) plus optional loop primers, judged against Eiken's own PrimerExplorer V5 criteria.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "design_lamp_primers"
  }
}

Input 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.
`gc_max`	No	GC FRACTION window, 0-1 (manual §2.3: "between about 40% to 65%") - upper bound. Unset = the preset for this template's GC class. Advanced.
`gc_min`	No	GC FRACTION window, 0-1 (manual §2.3: "between about 40% to 65%") - lower bound. Unset = the preset for this template's GC class. 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.
`max_sets`	No	how many sets to return, best first.
`length_max`	No	length window for the outer/inner binding regions (manual §4.2) - upper bound. Unset = the preset for this template's GC class. In nt. Advanced.
`length_min`	No	length window for the outer/inner binding regions (manual §4.2) - lower bound. Unset = the preset for this template's GC class. In nt. Advanced.
`region_end`	No	0-based inclusive end. Unset = the whole sequence. Advanced.
`tm_loop_max`	No	Tm window for the loop primers LF / LB - upper bound. Unset = the preset for this template's GC class. In °C. Advanced.
`tm_loop_min`	No	Tm window for the loop primers LF / LB - lower bound. Unset = the preset for this template's GC class. In °C. Advanced.
`loop_primers`	No	design LF/LB as well. They are optional in LAMP and accelerate the reaction.
`region_start`	No	0-based inclusive start of the region to design into (LAMP designs into a stretch, not a whole plasmid). Unset = the whole sequence; pass the selection's start to scope to it. Advanced.
`tm_inner_max`	No	Tm window for F1c / B1c - the manual's "about 65 °C" - upper bound. Unset = the preset for this template's GC class. In °C. Advanced.
`tm_inner_min`	No	Tm window for F1c / B1c - the manual's "about 65 °C" - lower bound. Unset = the preset for this template's GC class. In °C. Advanced.
`tm_outer_max`	No	Tm window for F2 / B2 / F3 / B3 - the manual's "about 60 °C" - upper bound. Unset = the preset for this template's GC class. In °C. Advanced.
`tm_outer_min`	No	Tm window for F2 / B2 / F3 / B3 - the manual's "about 60 °C" - lower bound. Unset = the preset for this template's GC class. In °C. Advanced.
`loop_span_max`	No	5' of F2 to 5' of F1 - the portion that forms the loop (manual §2.5: 40-60) - upper bound. Unset = the preset for this template's GC class. In bp. Advanced.
`loop_span_min`	No	5' of F2 to 5' of F1 - the portion that forms the loop (manual §2.5: 40-60) - lower bound. Unset = the preset for this template's GC class. In bp. Advanced.
`outer_gap_max`	No	F3 to F2 and B3 to B2 gap. THE TWO AUTHORITIES DISAGREE here too: PrimerExplorer V5 says 0-60, the Eiken genome site 0-20 - upper bound. Unset = the preset for this template's GC class. In bp. Advanced.
`outer_gap_min`	No	F3 to F2 and B3 to B2 gap. THE TWO AUTHORITIES DISAGREE here too: PrimerExplorer V5 says 0-60, the Eiken genome site 0-20 - lower bound. Unset = the preset for this template's GC class. In bp. Advanced.
`end_stability_dg`	No	the terminal-6-base stability rule (manual §2.2: the ΔG "is -4 kcal/mol or less"). In kcal/mol. Advanced.
`end_stability_nt`	No	how many terminal bases the end-stability rule measures (manual §2.2: 6). In nt. Advanced.
`amplified_span_max`	No	F2 5' to B2 5', the amplified region. THE TWO AUTHORITIES DISAGREE: PrimerExplorer V5 says 120-160, the Eiken genome site 120-180; the default follows PrimerExplorer and this is the knob for the other reading - upper bound. Unset = the preset for this template's GC class. In bp. Advanced.
`amplified_span_min`	No	F2 5' to B2 5', the amplified region. THE TWO AUTHORITIES DISAGREE: PrimerExplorer V5 says 120-160, the Eiken genome site 120-180; the default follows PrimerExplorer and this is the knob for the other reading - lower bound. Unset = the preset for this template's GC class. In bp. Advanced.

Output Schema

Name	Required	Description
`b3`	Yes	the best set's B3 outer primer
`f3`	Yes	the best set's F3 outer primer
`bip`	Yes	the best set's BIP (B1c + B2), as ordered
`fip`	Yes	the best set's FIP (F1c + F2), as ordered
`sets`	Yes	the primer sets, best first: six regions in the literature order with every measurement that decided each one
`offset`	Yes	where the designed-in stretch starts in the record: add it to every position above for record coordinates. 0 unless a region was given
`setCount`	Yes	how many sets were found
`constraints`	Yes	every window the search actually ran under, so a readout never has to restate them or guess which preset applied
`targetClass`	Yes	which preset the search ran under - atRich, normal or gcRich, chosen from the template's own GC content (manual §4.3)
`penaltyTerms`	Yes	what the best set's rank is MADE OF - one entry per criterion with the value measured, the window it was judged against and its cost. The costs sum to the penalty

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A3.7/5.0

Behavior3/5

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

Annotations already declare destructiveHint=false and openWorldHint=false, so the safety profile is largely covered; readOnlyHint=false is not contradicted by the description, which describes a computation rather than a read. The description adds real context by disclosing that candidates are judged against Eiken's PrimerExplorer V5 criteria, but omits the significant behavior that nearly every tuning knob defaults to a GC-class preset and that PrimerExplorer and the Eiken genome site disagree on some limits.

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?

One well-formed sentence, front-loaded with the action and the deliverable, with the judging criterion trailing as useful qualification. No filler, no repetition of the title, nothing to cut.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 24 parameters, 0 required fields and a nested _subject object, the description never states what input is minimally needed to run a design (a sequence, accession, sample id or file, optionally scoped by region_start/region_end). An output schema exists so return values need no explanation, but the omission of the input requirement leaves a real gap for an agent facing an all-optional schema.

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 carries the semantics of all 24 parameters, including the GC/Tm/length windows and the PrimerExplorer-vs-Eiken disagreement notes. The description only restates the F3/B3/FIP/BIP output set and the optionality of loop primers, which maps loosely to the loop_primers flag but adds no new parameter meaning. Baseline 3 applies.

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 plus specific resource: 'Design LAMP primer SETS' with an explicit product inventory (F3, B3, FIP, BIP plus optional loop primers) and the criteria used to judge them. The word LAMP (isothermal) clearly separates it from the many PCR/qPCR primer siblings like design_primers, design_primer_pairs and design_qpcr_assay.

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?

Usage is implied rather than stated: an agent can infer this is the tool for isothermal LAMP assays and that loop primers are optional, but the description names no alternatives and gives no when-not guidance (e.g. use design_primers for PCR, or design_bisulfite_primers for methylated templates). With ~20 primer-design siblings, an explicit routing sentence would have been valuable.

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?