jean — Molecular Biology & Genomics

design_ish_probes

Read-only

Design an in-situ hybridization probe against the subject: tile it into candidate oligos that meet a melting-temperature, G+C and composition specification, screen them for off-target binding against an alignment, and gather the survivors into the set that images best. Merges OligoMiner's tiling and its trained specificity model with iFISH's probe-set selection; each stage reports what it removed and why.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`dnac1`	No	concentration of the higher-concentration strand, typically the probe, in the melting-temperature calculation (OligoMiner `--dnac1`). In nM.
`dnac2`	No	concentration of the lower-concentration strand, typically the target (OligoMiner `--dnac2`). The Tm uses dnac1 − dnac2/2, so equal values halve the effective concentration. In nM.
`_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 to accept. In %.
`max_tm`	No	highest melting temperature to accept. In °C.
`min_gc`	No	lowest percent G+C to accept. In %.
`min_tm`	No	lowest melting temperature to accept, AFTER the formamide correction. In °C.
`origin`	No	coordinate of the subject's first base, when it is a window cut from a larger sequence. Read from a UCSC-style `range=` header when the subject carries one. Advanced.
`probes`	No	how many probe sets to return. Only applies when oligos_per_probe is set.
`sodium`	No	monovalent cation concentration of the hybridization buffer. In mM.
`overlap`	No	report every window that qualifies, including overlapping ones. Off by default because overlapping oligos cannot be used together in one probe. Advanced.
`rank_by`	No	feature that ranks the sets inside that band. Values: centrality (Centrality on the region), size (Compactness), homogeneity (Even spacing). Only applies when oligos_per_probe is set. Advanced.	size
`spacing`	No	bases forced between consecutive oligos. In nt. 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.
`filter_by`	No	feature that defines the band of acceptable sets. Values: centrality (Centrality on the region), size (Compactness), homogeneity (Even spacing). Only applies when oligos_per_probe is set. Advanced.	centrality
`formamide`	No	formamide in the hybridization buffer; it lowers every melting temperature by about 0.65 °C per percent. In %.
`max_length`	No	longest oligo to accept; the tiler grows a window until one fits, so a wide range yields more probes. In nt.
`min_length`	No	shortest oligo to accept. In nt.
`prohibited`	No	comma-separated subsequences an oligo may not contain; the default bans homopolymer runs, which hybridize promiscuously. Advanced.	AAAAA,TTTTT,CCCCC,GGGGG
`screen_mode`	No	trained model (recovers usable probes near repeats) · unique alignment only (strict) · no alignment at all (for a sequence that should be absent). Values: lda (Trained model), unique (Unique alignment only), zero (No alignment at all). Only applies when alignment_sam is set.	lda
`alignment_sam`	No	SAM the candidates were aligned with, for off-target screening. Without it the oligos are returned UNSCREENED and the result says so.
`filter_threshold`	No	width of the band around the best set, as a fraction of its own value. Only applies when oligos_per_probe is set. Advanced.
`oligos_per_probe`	No	oligos to gather into one probe. Leave unset to return every surviving oligo instead of a set.
`hybridization_temperature`	No	temperature the specificity model was trained at. Only these six exist; the coefficients change sign across the range, so an intermediate value is a different model rather than a blend. In °C. Only applies when alignment_sam is set.
`max_off_target_probability`	No	keep an oligo whose modelled chance of a real off-target site is below this. Only applies when alignment_sam is set. Advanced.

Output Schema

TableJSON Schema

Name	Required	Description
`oligos`	Yes	every oligo that survived all stages, in target order
`probes`	Yes	the chosen probe sets, best first, each with its oligos and its three scores
`stages`	Yes	what each stage took in, put out, and removed - with the reasons named
`coverage`	Yes	the coverage track, gaps, spacings and the Tm/G+C distributions a renderer draws
`oligoCount`	Yes	how many oligos survived
`explanation`	Yes	the derivation chain: conclusion, interpretation and machinery, generated from this run
`coveredFraction`	Yes	fraction of the target covered by at least one surviving oligo (0-1)

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context: multi-stage tiling, off-target screening against an alignment, gathering survivors into the best-imaging set, and reporting what each stage removed. It does not restate that alignment_sam is optional and yields unscreened oligos when absent, but that is documented in the schema.

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?

Two sentences, front-loaded with the core verb and resource. The first sentence maps the pipeline; the second adds algorithm provenance and reporting behavior. No filler, and the length is appropriate for a complex design tool.

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?

With 25 parameters, a nested subject object, and an output schema, the description still gives an agent the full workflow context needed to understand the tool's role. It does not spell out mode switches such as oligos_per_probe set vs unset or that screening requires alignment_sam, but those are covered in the schema and output schema, so it is largely 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 schema already documents all 25 parameters, including defaults, ranges, and enums. The description groups parameter domains—melting-temperature/G+C/composition specification, alignment screening, probe-set selection—but adds no parameter-level meaning beyond what the schema provides. Baseline 3 is appropriate.

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 an in-situ hybridization probe against the subject.' It further distinguishes itself from sibling probe-design tools by naming ISH and outlining the tiling, screening, and set-selection scope. An agent can identify the tool without opening the schema.

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

Usage Guidelines4/5

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

The description gives clear context for when to use it: designing ISH probes against a subject, with optional alignment-based screening and probe-set selection. It does not explicitly name alternatives such as design_hcr_probes or design_padlock_probes, nor does it state when not to use it, so it lacks exclusions.

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?