Jean by Melad Labs

design_saturation_primers

Design site-saturation mutagenesis (SSM) primers: one overlapping forward/reverse pair per site, each carrying a degenerate codon, sharing ONE reaction-level overlap and 3' temperature so every site amplifies in the same tube (both of Mutation Maker's solvers: fast approximation by default, exhaustive search on request).

Input 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. Advanced.
`cds`	Yes	the CDS nucleotide sequence, in frame from the start codon (length must be a multiple of 3).
`dntp`	No	total dNTP concentration, which chelates magnesium and so lowers the effective Mg²⁺. In mM. Advanced.
`tris`	No	Tris concentration. In mM. Advanced.
`dnac1`	No	the higher-concentration strand (the primer, in a large excess). In nM. Advanced.
`dnac2`	No	the lower-concentration strand (the template). In nM. Advanced.
`sites`	Yes	the saturation sites, comma- or space-separated, as [WT][pos]X — e.g. "V2X, K107X". 1-based residue positions.
`_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.
`solver`	No	which of Mutation Maker's two solvers designs the pairs. `fast` grows one candidate per site per temperature combination (upstream's own default, milliseconds). `exhaustive` enumerates every primer of every allowed length at every allowed start and scores every geometrically valid pair — hundreds of thousands per site, seconds rather than milliseconds, and it reports what it searched. Values: fast (Fast approximation), exhaustive (Exhaustive search).	fast
`_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.
`precision`	No	decimal places the reported Tm is rounded to. In dp. Advanced.
`oligo_prefix`	No	prefix for the designed oligo names. Advanced.	ssm
`five_end_flank`	No	explicit 5' flanking sequence — only for a free-standing gene with no plasmid open, and then the 3' flank is required too. Advanced.
`forward_primer`	No	5' flanking primer, 5'→3'. Left empty, it is read off the open plasmid 56 bp either side of the CDS (22 nt, and only when it occurs there exactly once).
`max_gc_content`	No	highest GC accepted. In %. Advanced.
`min_gc_content`	No	lowest primer GC accepted before a primer is flagged out of range. In %. Advanced.
`reverse_primer`	No	3' flanking primer, 5'→3' on its own strand. Left empty, it is read off the open plasmid 56 bp either side of the CDS (22 nt, and only when it occurs there exactly once).
`max_primer_size`	No	longest whole primer. In nt. Advanced.
`min_primer_size`	No	shortest whole primer. In nt. Advanced.
`salt_correction`	No	salt-correction method, in Biopython's `saltcorr` order. Values: No (None), Schildkraut_1965 (Schildkraut & Lifson 1965 (16.6 · log[Na⁺])), Wetmur_1991 (Wetmur 1991 (16.6 · log[Na⁺/(1 + 0.7 · Na⁺)])), SantaLucia_1996 (SantaLucia 1996 (12.5 · log[Na⁺])), SantaLucia_1998 (SantaLucia 1998 (11.7 · log[Na⁺])), SantaLucia_DeltaS_1998 (SantaLucia 1998, entropy (corrects ΔS, not Tm)), Owczarzy_2004 (Owczarzy 2004 (GC-dependent, corrects 1/Tm)), Owczarzy_2008 (Owczarzy 2008 (Mg²⁺ decision tree, dNTP-corrected)). Advanced.	Owczarzy_2004
`three_end_flank`	No	explicit 3' flanking sequence, the partner of `five_end_flank`. Advanced.
`degenerate_codon`	No	the degenerate codon installed at every site (NNK is the common 32-codon choice).	NNK
`max_overlap_size`	No	longest overlap. Upstream's scan stops two short of this (a reproduced quirk, see the port header). In nt. Advanced.
`min_overlap_size`	No	shortest shared overlap. In nt. Advanced.
`gc_content_weight`	No	score weight on GC overflow. Upstream's default is 0, and its GC term counts G twice and never counts C (a reproduced bug, see the port header) — raising this weight makes that quirk observable. Advanced.
`max_five_end_size`	No	longest 5' arm before the mutated codon. In nt. Only applies when solver is exhaustive. Advanced.
`min_five_end_size`	No	shortest 5' arm before the mutated codon. In nt. Advanced.
`max_three_end_size`	No	longest 3' arm beyond the mutated codon. Bounds the search area and discards candidates whose 3' arm overruns it. In nt. Only applies when solver is exhaustive. Advanced.
`min_three_end_size`	No	shortest 3' arm beyond the mutated codon. In nt. Advanced.
`overlap_temp_range`	No	width of the overlap Tm window. In °C. Advanced.
`overlap_temp_weight`	No	score weight on overlap Tm deviation. Advanced.
`three_end_temp_range`	No	width of the 3'-end Tm window scanned around each candidate temperature. In °C. Advanced.
`three_end_size_weight`	No	score weight on 3'-end length deviation. Advanced.
`three_end_temp_weight`	No	score weight on 3'-end Tm deviation. Advanced.
`max_overlap_temperature`	No	highest overlap Tm allowed. In °C.
`min_overlap_temperature`	No	lowest overlap Tm the reaction may settle on. In °C.
`overlap_temp_range_step`	No	step between overlap temperatures tried. In °C. Advanced.
`exclude_flanking_primers`	No	take the 3' Tm window from the explicit min/max above instead of from the flanking pair's own Tm. Advanced.
`compute_hairpin_homodimer`	No	add the hairpin/homodimer/heterodimer penalty to the score (roughly doubles the run; off upstream). Advanced.
`max_three_end_temperature`	No	highest 3'-end Tm allowed. In °C.
`min_three_end_temperature`	No	lowest 3'-end Tm (used when `exclude_flanking_primers` is on; otherwise the window comes from the flanking pair). In °C. Only applies when exclude_flanking_primers is true.
`three_end_temp_range_step`	No	step between 3'-end temperatures tried. In °C. Advanced.
`hairpin_temperature_weight`	No	score weight on hairpin Tm. Only applies when compute_hairpin_homodimer is true. Advanced.
`primer_dimer_temperature_weight`	No	score weight on homo/heterodimer Tm. Only applies when compute_hairpin_homodimer is true. Advanced.
`separate_forward_reverse_temperatures`	No	optimise the forward and reverse 3' temperatures independently. Advanced.

Output Schema

Name	Required	Description
`pairs`	Yes	one designed forward/reverse pair per site, with its overlap, temperatures, GC and in-range flags
`search`	Yes	what the solver actually searched: candidates enumerated and kept, pairs scored, temperature combinations tried. Null for the fast solver, which enumerates nothing
`siteCount`	Yes	sites requested
`foundCount`	Yes	sites the solver found a pair for (< siteCount means the parameters were too tight for some)
`fullSequence`	Yes	the construct the design spans, flanking primer to flanking primer
`forwardTemperature`	Yes	reaction-level forward 3'-end Tm
`overlapTemperature`	Yes	the ONE overlap Tm the whole reaction settled on
`reverseTemperature`	Yes	reaction-level reverse 3'-end Tm

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 25, 2026
- addedOutput schema / properties / forwardTemperature / x-unit
```
Added value: +"°C"
```
- addedOutput schema / properties / overlapTemperature / x-unit
```
Added value: +"°C"
```
- addedOutput schema / properties / reverseTemperature / x-unit
```
Added value: +"°C"
```
First observedOct 20, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the safety profile is already given. The description adds genuine design semantics — every site is constrained to a common overlap and 3' temperature — but it says nothing about the dependency on an open plasmid for flanking primers, and its solver-behaviour detail (milliseconds vs seconds) is largely restated from the solver parameter description.

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?

A single front-loaded sentence that leads with the verb and resource before the technical constraints, with no filler. It is dense and parenthesis-heavy, but every clause (per-site pair, degenerate codon, shared overlap/temperature) carries information.

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?

An output schema and annotations are present and the schema documents all 47 parameters, so the description doesn't need to cover returns or parameter defaults. However, for a tool this large the description omits the operational precondition (flanking primers read from the open plasmid unless supplied) and any recommendation on fast versus exhaustive, leaving real gaps.

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 parameter burden, including the solver trade-off and the flanking-primer fallback. The description adds no parameter-level meaning beyond it, 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?

States a specific verb and resource ('Design site-saturation mutagenesis (SSM) primers') and pins down the output shape: one overlapping forward/reverse pair per site, each with a degenerate codon, all sharing a single reaction-level overlap and 3' temperature. That combination of per-site saturation plus one shared reaction condition implicitly separates it from single-site mutagenesis and generic degenerate-primer design, but no sibling is named, so the differentiation must be inferred.

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?

The 'same tube' framing implies the use case (multiplexed SSM libraries) and the parenthetical notes that fast is the default solver with exhaustive 'on request'. There is no explicit when-to-use/when-not guidance and no routing away from the many neighbouring design_* primer tools, so the agent must read the schemas to choose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Jean by Melad Labs 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?