jean — Molecular Biology & Genomics

score_overhang_fidelity

Read-only

Score a Golden Gate junction (fusion-site) set against MEASURED T4 DNA ligase end-joining data. It is the number NEB's Ligase Fidelity Viewer reports: the expected fraction of assemblies in which EVERY junction ligated correctly. This is the quantitative counterpart to check_golden_gate_parts: that says whether the parts will be cut, this says whether the pieces will go back together in the right order. Wire golden_gate_assemble's overhangs output straight into it.

Input Schema

TableJSON Schema

Name	Required	Description
`_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.
`enzyme`	No	the Type-IIS enzyme the reaction uses, which picks that enzyme's own measured matrix when one exists. Only applies when dataset is not given.
`dataset`	No	score against this measured matrix instead of the one the enzyme implies. Values: BsaI-HFv2 (BsaI-HFv2, Golden Gate cycling (4 nt)), BsmBI-v2 (BsmBI-v2, Golden Gate cycling (4 nt)), Esp3I (Esp3I, Golden Gate cycling (4 nt)), BbsI-HF (BbsI-HF, Golden Gate cycling (4 nt)), SapI (SapI, Golden Gate cycling (3 nt)), T4-01h-25C (T4 DNA ligase, 1 h at 25 C (4 nt)), T4-01h-37C (T4 DNA ligase, 1 h at 37 C (4 nt)), T4-18h-25C (T4 DNA ligase, 18 h at 25 C (4 nt)), T4-18h-37C (T4 DNA ligase, 18 h at 37 C (4 nt)).
`_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.
`remedies`	No	also compute what to CHANGE: the drop-the-worst repair, and replacement candidates for each flagged junction. Off makes the run cheaper on a large set.
`overhangs`	Yes	the junction overhangs, one per junction, top strand (e.g. AATG, GCTT). Wire `golden_gate_assemble.overhangs` here, or list them.
`replacements_per_junction`	No	how many replacement candidates to rank per flagged junction. Advanced.

Output Schema

TableJSON Schema

Name	Required	Description
`flags`	Yes	weak, self-misannealing and cross-misannealing junction indices, plus the structural verdict
`worst`	Yes	the weakest junctions, worst first: what to change to raise the score
`repair`	Yes	the drop-the-worst repair: which junctions to remove, what is left, and the fidelity that leaves. Null when `remedies` is off
`dataset`	Yes	the measured matrix actually scored against
`percent`	Yes	the same number as a percentage, which is how every incumbent reports it
`fidelity`	Yes	expected fraction of fully-correct assemblies, 0-1
`junctions`	Yes	per junction: overhang, correct/total measured events, its own fidelity, Watson-Crick strength, and its strongest mismatch partners
`meaningful`	Yes	false when a STRUCTURAL error makes the fidelity number misleading rather than merely bad: do not present `fidelity` on its own when this is false
`replacements`	Yes	per FLAGGED junction, the best overhangs to swap in, each with the whole set’s fidelity after the swap. Empty when `remedies` is off
`atMeasurementCeiling`	Yes	true when NO mismatch ligation was measured between any two junctions, so the score is exactly 100%: the floor the source experiment can resolve, not a guarantee

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds real context by explaining what the returned number means (the NEB Ligase Fidelity Viewer metric) and that scoring is against measured T4 ligase data, though it doesn't discuss cost beyond what the schema's remedies param already notes.

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?

Four sentences, each earning its place: purpose/metric definition, the sibling contrast, and the wiring instruction. Front-loaded with the core action and no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be explained, and the description covers purpose, the sibling alternative, and how to feed the overhangs parameter. Nothing an agent needs to call it correctly is missing.

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 seven parameters. The description's wiring hint for overhangs largely repeats the schema's own note ('Wire golden_gate_assemble.overhangs here'), so it adds little beyond structured data. 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 (score) and resource (a Golden Gate junction/fusion-site overhang set) and defines the metric precisely as the expected fraction of assemblies in which every junction ligated correctly. It explicitly distinguishes itself from the sibling check_golden_gate_parts, so an agent can tell them apart without opening either schema.

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

Usage Guidelines5/5

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

Names the alternative (check_golden_gate_parts) and the exact condition that selects between them ('whether the parts will be cut' vs 'whether the pieces go back together in the right order'). It also gives a concrete integration instruction: wire golden_gate_assemble's overhangs output straight into it.

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?