jean — Molecular Biology & Genomics

design_padlock_probes

Read-only

Design padlock probes for in-situ sequencing against the subject: find the two-arm targets whose melting temperature falls in a window, check each against a BLAST search for any other transcript that could be ligated across the junction, pack non-overlapping targets from the 3' end, and assemble each into its padlock with the backbone given. Without BLAST results it returns the targets to search, and says the junction check has not been run.

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_tm`	No	highest target melting temperature to accept (exclusive). In °C.
`min_tm`	No	lowest target melting temperature to accept (exclusive), at 0.1 µM probe, 75 mM monovalent, 10 mM divalent salt and 20% formamide. In °C.
`barcode`	No	the barcode read out by sequencing. Advanced.	XXXX
`_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.
`interval`	No	fewest bases between two packed targets. In nt.
`variants`	No	comma-separated accessions (no version) that count as the target itself, such as its isoforms. Empty: a hit counts as the target only when its accession is in the subject's name. Only applies when blast_csv is set. Advanced.
`blast_csv`	No	blastn -outfmt 10 output for the targets FASTA this tool returns (run with -word_size 7 -strand plus against your transcriptome). Without it no target is checked for junction specificity.
`arm_length`	No	length of each target arm; the target is twice this. In nt.
`linker_upstream`	No	backbone sequence between the 3' arm and the barcode. Advanced.	LINKERFIRST
`linker_downstream`	No	backbone sequence between the barcode and the 5' arm. Advanced.	LINKERSECOND

Output Schema

TableJSON Schema

Name	Required	Description
`packed`	Yes	every packed target before the database-mappability filter. Null until `blast_csv` is given
`padlocks`	Yes	the final padlock probes (target found in the database), each with its start, target, full sequence and Tm. Null until `blast_csv` is given: the junction check has not been run
`explanation`	Yes	the derivation chain: conclusion, interpretation and machinery, generated from this run
`padlockCount`	Yes	how many padlock probes survived. Null until `blast_csv` is given, because a 0 would read as none surviving a check that has not been run
`targetsFasta`	Yes	the melting-temperature-passing targets as FASTA, named target_N, for blastn

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 declare a safe read-only, non-destructive, closed-world computation. The description adds real behavioral context beyond that: the two-phase nature of the tool and the degraded-output contract when BLAST results are absent (returns targets and flags the junction check as not run). This is useful disclosure of output behavior that annotations do not cover.

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?

Front-loaded with the verb+resource, then two dense workflow sentences. Every clause describes a distinct step or fallback behavior, so it earns its length, though the second sentence is somewhat packed.

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?

For a complex 11-parameter tool, the description covers the pipeline, the BLAST prerequisite, and the fallback behavior, and an output schema exists so return values need not be explained. Sufficient for correct invocation, with only minor gaps around alternative tools.

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 each parameter is already documented in the schema, and the description adds only workflow-level framing for the Tm window, BLAST input, packing interval and backbone rather than new syntax or format detail. Baseline 3 is appropriate when the schema carries the parameter burden.

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 (design) and resource (padlock probes) for in-situ sequencing, then enumerates the actual steps: Tm-windowed two-arm target finding, BLAST junction specificity check, 3'-end packing of non-overlapping targets, and padlock assembly. This clearly differentiates it from sibling probe designers like design_ish_probes or design_hcr_probes.

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?

Clearly conveys the operational context: it explains what happens with and without blast_csv, telling the agent the prerequisite for a full run versus the partial run that only returns targets. It does not, however, explicitly name alternative sibling tools or state when to choose this over them.

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?