jean — Molecular Biology & Genomics

screen_guides

Read-only

Screen guide spacers the way CHOPCHOP does before it accepts them: GC gate, self-complementary hairpins inside the spacer, and hairpins against the sgRNA backbone. A guide that folds onto its own scaffold is loaded into Cas9 poorly however good its on-target score is, so this is the check that explains a guide with a good score and no activity.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`gg`	No	the construct starts the transcript GG — upstream's `-gg` REPLACES the spacer's first two bases with G (T7 preference), it does not lengthen it. Advanced.
`pre_g`	No	the construct prepends a single 5' G (upstream's `-preG`) — this one lengthens the scanned string, and upstream's fixed 17-window loop then never reaches its last bases. Advanced.
`_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.
`spacers`	Yes	the protospacers to screen (20 nt for SpCas9) — wire `topSpacer` or the spacers out of a design run, or list them.
`_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.
`backbone`	No	which sgRNA backbone the spacer will be cloned into — the hairpin test is against this. Values: original (original gRNA backbone), extended (extended backbone (Cas9-GFP tracking)).	original

Output Schema

TableJSON Schema

Name	Required	Description
`clean`	Yes	the spacers that passed the GC gate and flagged no hairpin — the ones to take forward
`counts`	Yes	upstream's own four summary counts: total, after the GC screen, with a self hairpin, with a backbone hairpin
`screened`	Yes	per spacer: GC, whether it was dropped by the GC gate, the two hairpin verdicts, and every flagged 4-mer with its position
`backboneLabel`	Yes	which backbone the run screened against

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuine behavioral rationale beyond that: it explains that scaffold folding impairs Cas9 loading regardless of on-target score, clarifying the pass/fail logic an agent should expect.

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?

Two sentences, front-loaded with the action and the checks, with the rationale following. Some phrasing is chatty ('the way CHOPCHOP does', 'however good its on-target score is'), but no sentence is wasted.

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 cover the safety profile. The description supplies the domain mechanism and the diagnostic use case, leaving little an agent needs beyond what structured fields provide.

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 six parameters (spacers, gg, pre_g, backbone, _subject, _files) in detail. The description adds no parameter-level guidance, so the baseline 3 applies.

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?

Names a specific verb (screen) and resource (guide spacers) and enumerates the actual checks performed: GC gate, self-complementary hairpins, and hairpins against the sgRNA backbone. It does not, however, explicitly distinguish itself from related siblings like fold_guide or crispr_design_guides, so the reader must infer the boundary.

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?

Provides a clear usage scenario: run this before accepting guides (the CHOPCHOP-style pre-acceptance gate) and as the diagnostic when a guide scores well but shows no activity. No explicit alternatives or exclusions are given, so it never says 'use X instead'.

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?