Jean by Melad Labs

design_primer_pairs

The Primer Designer's own ranked search: scan the open record for primer pairs inside a product-size, Tm, length and GC window, score every candidate on Tm, dimers, hairpins, 3' stability, repeats, clamp and specificity under weights you set, and return the best N.

Input Schema

Name	Required	Description	Default
`task`	No	`new` ranks candidate pairs; `existing` keeps the primer you supply and designs its mate.	new
`_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	highest primer GC accepted. In %.
`gc_min`	No	lowest primer GC accepted. In %.
`n_pairs`	No	how many ranked pairs to return.
`_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.
`excluded`	No	spans no primer may sit on, as find_primer_snps' `excluded` emits them: a list of {start, end}, 0-based and end-exclusive, where start = end is an insertion between two bases. The amplicon may run across them. The panel's Avoid known SNPs. Advanced.
`fwd_tail`	No	5' non-annealing tail added to every forward primer (a restriction site or adapter). The footprint, and so binding and Tm, is unchanged. Advanced.
`rev_tail`	No	5' non-annealing tail added to every reverse primer. Advanced.
`target_tm`	No	the Tm each primer is scored toward. In °C.
`weight_gc`	No	scoring weight for the `gc` penalty (0 switches it off). Advanced.
`weight_tm`	No	scoring weight for the `tm` penalty (0 switches it off). Advanced.
`conditions`	No	salt, magnesium, dNTP and oligo concentrations plus the salt-correction method the Tm window is measured in. Left unset it is filled from your reaction-conditions settings, as the panel's are. Advanced.
`region_end`	No	0-based inclusive end of the region to design within. Advanced.
`target_end`	No	0-based inclusive end of the target. Advanced.
`weight_end3`	No	scoring weight for the `end3` penalty (0 switches it off). Advanced.
`region_start`	No	0-based inclusive start of the region to design within. Unset = the whole template. Advanced.
`target_start`	No	0-based inclusive start of a target the amplicon must flank, with no primer on it. Advanced.
`tm_window_max`	No	highest primer Tm accepted at all. In °C.
`tm_window_min`	No	lowest primer Tm accepted at all. In °C.
`weight_length`	No	scoring weight for the `length` penalty (0 switches it off). Advanced.
`weight_poly_x`	No	scoring weight for the `polyX` penalty (0 switches it off). Advanced.
`weight_hairpin`	No	scoring weight for the `hairpin` penalty (0 switches it off). Advanced.
`weight_tm_pair`	No	scoring weight for the `tmPair` penalty (0 switches it off). Advanced.
`weight_gc_clamp`	No	scoring weight for the `gcClamp` penalty (0 switches it off). Advanced.
`weight_self_end`	No	scoring weight for the `selfEnd` penalty (0 switches it off). Advanced.
`existing_forward`	No	with `task: existing`, the forward primer to keep. Only applies when task is existing.
`existing_reverse`	No	with `task: existing`, the reverse primer to keep. Only applies when task is existing.
`product_size_max`	No	longest acceptable amplicon. In bp.
`product_size_min`	No	shortest acceptable amplicon. In bp.
`weight_cross_end`	No	scoring weight for the `crossEnd` penalty (0 switches it off). Advanced.
`weight_di_repeat`	No	scoring weight for the `diRepeat` penalty (0 switches it off). Advanced.
`primer_length_max`	No	longest primer. In nt.
`primer_length_min`	No	shortest primer. In nt.
`weight_mispriming`	No	scoring weight for the `mispriming` penalty (0 switches it off). Advanced.
`weight_self_dimer`	No	scoring weight for the `selfDimer` penalty (0 switches it off). Advanced.
`mispriming_library`	No	a Primer3 repeat library to screen every primer against. `none` skips the screen. Advanced.	none
`weight_cross_dimer`	No	scoring weight for the `crossDimer` penalty (0 switches it off). Advanced.
`weight_specificity`	No	scoring weight for the `specificity` penalty (0 switches it off). Advanced.

Output Schema

Name	Required	Description
`ta`	Yes	the top pair's annealing temperature [°C]
`pairs`	Yes	every returned pair in rank order: score, both primers (sequence, span, Tm, GC), product length, Tm and Ta
`forward`	Yes	the top pair's forward primer (wire into pcr_amplify)
`reverse`	Yes	the top pair's reverse primer
`pairCount`	Yes	how many pairs came back
`shortfall`	Yes	why fewer pairs came back than were asked for; empty when the run was not short
`productLen`	Yes	the top pair's amplicon length [bp]

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 25, 2026
- addedOutput schema / properties / productLen / x-unit
```
Added value: +"bp"
```
- addedOutput schema / properties / ta / x-unit
```
Added value: +"°C"
```

Changed1 schema field changedOct 23, 2026

addedInput schema / properties / conditions / properties / selfcomp

Added value: +{
+  "description": "both strands are one self-complementary oligo (the concentration term becomes dnac1 rather than dnac1 − dnac2/2).",
+  "type": "boolean"
+}

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 declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is largely covered. The description adds genuine behavioral context: candidates are scored under user-set weights, and windows act as hard filters while weights shape ranking. It does not disclose cost/runtime (a 39-parameter combinatorial search), determinism, or what happens when no pair fits the windows.

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 what is scanned, then how it is scored, then what is returned — a sensible pipeline order with no filler. It is dense but every clause carries content; only the list of scoring terms is long enough to warrant breaking into a second sentence.

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 tool with nested condition objects, an output schema, and many near-neighbour design tools, the description gives a good high-level frame but omits workflow placement — e.g., pairing with find_primer_snps for the `excluded` spans or primer_check for validation. Because the schema and output schema carry the detail, this is adequate rather than complete.

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 baseline is 3. The description does map its scoring categories (Tm, dimers, hairpins, 3' stability, repeats, clamp, specificity) onto the weight_* families, which helps an agent understand the parameter surface as a whole, but it adds no per-parameter meaning or defaults beyond what the schema already documents.

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?

The description states a specific verb and resource: it scans a record for primer pairs inside windows, scores candidates on named criteria, and returns the best N. That is far more informative than the tool name alone. It stops short of distinguishing itself from the many sibling design tools (design_primers, design_qpcr_assay, design_degenerate_primers, design_bisulfite_primers) — 'The Primer Designer's own ranked search' gestures at a panel implementation rather than telling an agent which design tool to pick.

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?

There is no explicit when-to-use, when-not-to-use, or alternative naming. An agent facing ~10 primer-design siblings gets no rule for choosing this one, and prerequisites (needs an open record, reaction conditions settings) are only hinted at. The only routing signal is implicit in 'inside a product-size, Tm, length and GC window'.

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?