jean — Molecular Biology & Genomics

screen_molecule_library

Read-only

Screen every structure of a library at once against drug-likeness rules and structural-alert catalogs, as the library grid does, and bin one rule property across it, split at the bound of a chosen rule. Returns, per 0-based structure, the rules it breaks and the alerts it trips, and the binned distribution with how many structures fall within the bound.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`bins`	No	how many bins.
`rules`	No	which drug-likeness rules to screen, by id. Every rule by 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.
`_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.
`property`	No	the rule property to bin, at the value the rules judged. Values: mw (Monoisotopic mass), clogp (cLogP (Crippen)), hbd (H-bond donors), hba (H-bond acceptors), lipinskiHbd (Lipinski donors (NH + OH)), lipinskiHba (Lipinski acceptors (N + O)), hbonds (Donors + acceptors), tpsa (TPSA (N and O only)), rotatableBonds (Rotatable bonds), rings (Rings), heavyAtoms (Heavy atoms), numAtoms (Atoms in the graph), molarRefractivity (Molar refractivity (Crippen)), averageMw (Molecular weight (average)), totalAtoms (Atoms, hydrogens included), formalCharge (Net formal charge).	mw
`molecules`	Yes	the library: one SMILES or molfile per entry.
`alert_sets`	No	which structural-alert catalogs to screen against. Empty screens nothing.
`split_rule`	No	the rule whose bound on that property splits each bar; the first screened rule bounding it by default. Values: rule_of_five (Lipinski rule of five), rule_of_five_beyond (Beyond rule of five), rule_of_four (Rule of four (PPI inhibitors)), rule_of_three (Rule of three (fragments)), rule_of_three_extended (Rule of three, extended), rule_of_two (Rule of two (building blocks)), rule_of_ghose (Ghose filter), rule_of_veber (Veber filter), rule_of_reos (REOS), rule_of_chemaxon_druglikeness (ChemAxon drug-likeness), rule_of_egan (Egan filter), rule_of_pfizer_3_75 (Pfizer 3/75), rule_of_gsk_4_400 (GSK 4/400), rule_of_oprea (Oprea lead-likeness), rule_of_xu (Xu drug-like index), rule_of_cns (CNS penetration), rule_of_respiratory (Respiratory (inhaled/nasal)), rule_of_five_paper (Lipinski rule of five (paper: average MW)), rule_of_ghose_paper (Ghose filter (paper: all atoms, average MW)), rule_of_reos_paper (REOS (paper: net charge bounded, average MW)).

Output Schema

TableJSON Schema

Name	Required	Description
`rows`	Yes	per structure: 0-based index, canonical SMILES, rules broken, alerts tripped
`summary`	Yes	how many structures pass clean, and how many fall within the split bound
`distribution`	Yes	the bins (lo, hi, within, outside), the bounds on the property and the split

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already establish the read-only, non-destructive, closed-world profile, so the bar is lower. The description adds genuine behavioral context beyond that: it explains the binning operation, that the split occurs at a chosen rule's bound, and what the result contains per structure. It does not state limits or performance characteristics, but the added semantics are solid.

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 dense sentences that front-load the core action and then the output. Most of the phrasing earns its place, though 'as the library grid does' is a slightly opaque aside that consumes space without adding precise meaning.

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 100% schema coverage, an output schema, and annotations covering the safety profile, the description only needs to frame the operation and how parameters relate. It does so adequately, leaving no critical gap for an agent to call the tool correctly.

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 a baseline of 3 applies. The description exceeds that by clarifying how property, split_rule, and rules interact - the property is binned at the bound of a chosen rule, and results are reported per structure - adding relational meaning the schema alone does not convey.

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?

The description states a specific verb and resource (screen a molecule library) and enumerates the two operations: screening against drug-likeness rules and alert catalogs, plus binning one property. It is clear what the tool does. However, it distinguishes itself from siblings only obliquely via 'as the library grid does' rather than naming assess_small_molecule, search_molecule_library, or compare_molecules.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance and no named alternative. The phrase 'as the library grid does' hints at a parallel tool but never says when this batch-screening tool should be chosen over sibling screening or comparison tools.

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?