jean — Molecular Biology & Genomics

design_hcr_probes

Read-only

Design HCR v3.0 split-initiator probe pairs against the subject: tile its reverse complement into 52 nt windows, drop windows with C or G runs, a stable hairpin, G+C or RNA:DNA free energy outside their windows, or (given a bowtie2 alignment of the tiles) more than one genome hit, then pick non-overlapping tiles closest to the target free energy and split each around a 2 nt gap into an odd and an even probe carrying half of the chosen amplifier's initiator. Each stage reports how many tiles it kept.

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.
`max_gc`	No	highest percent G+C of a tile. In %.
`min_gc`	No	lowest percent G+C of a tile. In %.
`channel`	No	HCR amplifier whose split initiator the pair carries; one channel per target in a multiplexed experiment.	B1
`dtm_max`	No	largest allowed difference between the halves' melting temperatures. In °C. Only applies when dtm_filter is true. 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_gibbs`	No	least stable RNA:DNA free energy to accept. In kcal/mol.
`min_gibbs`	No	most stable RNA:DNA free energy to accept (at 37 °C, 0.33 M Na⁺). In kcal/mol.
`tile_size`	No	length of the target window each pair covers, both halves and the 2 nt gap. In nt. Advanced.
`dtm_filter`	No	also require the two halves' melting temperatures to agree. Advanced.
`max_probes`	No	most probe pairs to return.
`target_gibbs`	No	free energy the selection ranks tiles by closeness to. In kcal/mol.
`alignment_sam`	No	SAM from bowtie2 -k 3 -f of the tiles FASTA this tool returns, against your genome or transcriptome. Without it no tile is checked for uniqueness and the result says so.
`max_hairpin_tm`	No	drop a tile whose primer3 hairpin melts at or above this. In °C. Advanced.
`max_run_length`	No	window length for the C and G run check. In nt. Advanced.
`num_hits_allowed`	No	most alignments a tile may have and still be kept (its own locus counts as one). Only applies when alignment_sam is set.
`max_run_mismatches`	No	bases in that window allowed to differ from the run base. In nt. Advanced.

Output Schema

TableJSON Schema

Name	Required	Description
`pairs`	Yes	the selected probe pairs, ranked by closeness to the target free energy, each with both oligos, its 1-based start, G+C, Tm, half-Tm difference, free energy and genome hits
`stages`	Yes	how many tiles each stage kept, in pipeline order
`pairCount`	Yes	how many probe pairs were selected
`orderTable`	Yes	every odd then every even oligo as a Name/Sequence table for plate ordering
`tilesFasta`	Yes	the tiles that pass the run and hairpin checks, as FASTA, for bowtie2 -k 3 -f
`explanation`	Yes	the derivation chain: conclusion, interpretation and machinery, generated from this run

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already cover the read-only safety profile, yet the description adds substantial behavioral context: the sequential filter stages, that each stage reports tiles kept, and critically that without alignment_sam no uniqueness check occurs and 'the result says so.' This goes meaningfully beyond the annotations.

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?

Purpose is front-loaded and the second sentence covers reporting behavior. It is dense — one long sentence enumerating every filter — but each clause describes a real pipeline stage, so little is wasted despite the length.

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?

An output schema exists, so return values need no explanation, and annotations carry the safety profile. The description supplies the algorithm, the parameter interplay, and the important edge case of a missing alignment, leaving it nearly complete for a 17-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds value by tying parameters into a coherent pipeline — the 52 nt tile and 2 nt gap mapping to tile_size, the amplifier initiator to channel, and the free-energy filters to their windows. It explains how parameters interact rather than restating them.

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?

States a specific verb and resource — 'Design HCR v3.0 split-initiator probe pairs' — and then details the exact algorithm, so an agent can immediately distinguish it from the many sibling design_*_probes tools (design_ish_probes, design_padlock_probes). The scope is concrete rather than tautological.

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 description implies usage by naming the HCR v3.0 technique and the optional bowtie2 alignment workflow, but it never states when to choose this over sibling probe-design tools or what prerequisites (e.g., a subject record) are required. Usage is inferable from the workflow description rather than explicit.

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?