jean — Molecular Biology & Genomics

design_multisite_primers

Design QCLM (quick-change lightning multi-site) oligos: one primer per mutated site, all annealing in one reaction, with the codons drawn from an organism's usage table. A design/write.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`k`	No	potassium concentration. In mM. Advanced.
`mg`	No	magnesium concentration — the term the Owczarzy corrections are most sensitive to. In mM. Advanced.
`na`	No	sodium concentration the salt correction is computed for. In mM. Only applies when gc_value_set is Schildkraut_1965 or Primer3 or Ahsen_2001. Advanced.
`cds`	Yes	the CDS nucleotide sequence, in frame from the start codon.
`dntp`	No	total dNTP concentration, which chelates magnesium and so lowers the effective Mg²⁺. In mM. Advanced.
`seed`	No	seed for the codon draw. The same seed and the same request give the same oligos; change it to re-roll.
`tris`	No	Tris concentration. In mM. Only applies when gc_value_set is Schildkraut_1965 or Primer3 or Ahsen_2001. 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.
`_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.
`organism`	No	codon-usage table the synonymous choice is drawn from.	e-coli
`mutations`	Yes	the substitutions, comma- or space-separated, as [WT][pos][MUT] — e.g. "E42L, E42W, K107M". Several entries at one position are ONE site delivering several aminos.
`precision`	No	decimal places the reported Tm is rounded to. In dp. Advanced.
`temp_weight`	No	score weight on Tm deviation. Advanced.
`use_primer3`	No	apply primer3 hairpin / homodimer / heterodimer penalties. Advanced.
`gc_value_set`	No	which published GC-formula parameter set the melting temperature is computed under. Values: QuickChange (QuikChange (the kit manufacturer’s own formula)), Chester_1993 (Marmur-Doty (Chester & Marshak 1993)), Schildkraut_1965 (Schildkraut & Lifson 1965 (Marmur-Doty + log[Na⁺])), Primer3 (Primer3Plus product Tm (Biopython’s default set)), Ahsen_2001 (von Ahsen 2001 (accuracy against ease of use)). Advanced.	QuickChange
`five_end_flank`	No	explicit 5' context. Left empty, 60 bp is read off the open record either side of the CDS. Advanced.
`max_gc_content`	No	highest GC accepted. In %. Advanced.
`min_gc_content`	No	lowest oligo GC accepted. In %. Advanced.
`max_primer_size`	No	longest oligo. In nt. Advanced.
`max_temperature`	No	highest Tm threshold swept. In °C.
`min_primer_size`	No	shortest oligo. In nt. Advanced.
`min_temperature`	No	lowest Tm threshold the growth scan sweeps. In °C.
`temp_range_size`	No	width of the acceptable Tm window around the reaction temperature. In °C. Advanced.
`three_end_flank`	No	explicit 3' context, the partner of `five_end_flank`. Advanced.
`gc_content_weight`	No	score weight on GC overflow. Advanced.
`max_five_end_size`	No	longest 5' lead. In nt. Advanced.
`min_five_end_size`	No	bases between the 5' terminus and the first mutated codon, minimum. In nt. Advanced.
`max_three_end_size`	No	longest 3' tail. In nt. Advanced.
`min_three_end_size`	No	bases between the last mutated codon and the 3' terminus, minimum. In nt. Advanced.
`primer_size_weight`	No	score weight on oligo length deviation. Advanced.
`temp_threshold_step`	No	step between Tm thresholds tried. In °C. Advanced.
`five_end_size_weight`	No	score weight on 5'-lead length deviation. Advanced.
`use_degeneracy_codon`	No	collapse a site's codons into one IUPAC-degenerate codon (upstream's default). Off, each amino gets its own oligo.
`three_end_size_weight`	No	score weight on 3'-tail length deviation. Advanced.
`non_overlapping_primers`	No	forbid oligos from overlapping each other. Upstream ranks only the LAST split's solutions with this on (a reproduced bug, see the port header). Advanced.
`mutation_coverage_weight`	No	score weight on how many of the requested aminos the design actually delivers — upstream's dominant term. Advanced.
`hairpin_temperature_weight`	No	score weight on hairpin Tm. Advanced.
`codon_usage_frequency_threshold`	No	discard synonymous codons rarer than this fraction in the chosen organism.
`primer_dimer_temperature_weight`	No	score weight on dimer Tm. Advanced.

Output Schema

TableJSON Schema

Name	Required	Description
`seed`	Yes	the seed this design was drawn with — change it to re-roll, keep it to reproduce
`oligos`	Yes	one oligo per site, with its span, Tm, GC and the degenerate codons it installs
`failureCount`	Yes	constraint breaches in the winning solution (0 = every oligo inside its limits)
`fullSequence`	Yes	the construct the oligo coordinates are on: flank + CDS + flank
`mutationCoverage`	Yes	fraction of the requested amino acids the design actually delivers, 0–1
`reactionTemperature`	Yes	the ONE annealing temperature the winning solution is built for

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false. The description's 'A design/write' confirms the write nature but adds no side-effect, mutation-of-state, or licensing/rate context beyond what annotations convey; an output schema covers the return. Adequate but thin.

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?

Two short sentences, mechanism front-loaded ahead of the terse write note. Efficient with no redundancy; the trailing 'A design/write' matters but is minimal.

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 39-parameter design tool with full schema coverage, non-destructive annotations, and an output schema, the description is complete enough to invoke but omits any note on what the design produces conceptually (primer set, coverage failure modes) or the meaning of dominant knobs like mutation_coverage_weight.

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 all 39 parameters (including the advanced salt/Tm/score-weight knobs) are documented in the schema itself. The description only alludes to the organism usage table, adding nothing beyond the schema's `organism` description. Baseline 3.

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?

States a specific verb (Design) and resource (QCLM multi-site oligos) and explains the mechanism ('one primer per mutated site, all annealing in one reaction'). It does not name the adjacent siblings (design_mutagenesis_primers, design_saturation_primers, design_fusion_site_primers), so the boundary is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use, when-not-to-use, or alternatives are given, despite a large cluster of primer-design siblings where routing matters. The implicit use case (multi-site mutagenesis) is inferable from the name alone.

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?