jean — Molecular Biology & Genomics

rank_tradeoffs

Read-only

Which candidates in a table are not beaten on every objective at once: Pareto (non-dominated) sorting of rows scored on several columns, each to maximise or minimise. Returns each candidate's front (1 = non-dominated), the candidate one front up that beats it, and its crowding distance within its front (how isolated it is, so a short list can be spread along the front). Rows can be filtered first (em_max>=580, agg=m), and rows with an empty objective are left out and counted, never ranked last. moocore 0.3.2's pareto_rank and is_nondominated, emoa 0.5-3's and pymoo 0.6.2's crowding distances, reproduced.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`label`	No	the column naming each candidate. Left unset, the first column.
`table`	Yes	the candidates: a header row, then one row per candidate. Comma- or tab-separated, quoted cells allowed.
`_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.
`filter`	No	keep only rows passing every clause, separated by commas: a column, one of = != >= <= > <, and a value (`em_max>=580, agg=m`). Numbers compare as numbers; a blank cell passes no ordering clause.
`_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.
`crowding`	No	how isolation along a front is measured: NSGA-II's normalised distance (each gap over the objective's range, averaged), or the raw sum of gaps in each objective's own units. Values: normalised (NSGA-II (normalised)), raw (raw gaps). Advanced.	normalised
`maximise`	No	the columns where higher is better, separated by commas.
`minimise`	No	the columns where lower is better, separated by commas.
`keep_duplicates`	No	keep every copy of candidates with identical values on the first front; off keeps the first copy and names it as what the others duplicate. Advanced.

Output Schema

TableJSON Schema

Name	Required	Description
`front`	Yes	the non-dominated candidates (front 1), most isolated first
`counts`	Yes	rows in the table, filtered out, left out for an empty objective, ranked
`fronts`	Yes	how many candidates sit on each front
`ranked`	Yes	every candidate ranked: front, flag, crowding distance, the candidate that beats it, its objective values

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already declare a safe read-only, non-open-world operation, and the description adds substantial beyond them: the return shape (front number, the one-front-up dominator, crowding distance), filter-then-rank ordering, and the notable rule that rows with an empty objective are dropped and counted rather than ranked last. It even cites the source algorithms (moocore, emoa, pymoo) whose behavior is reproduced.

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?

Purpose is front-loaded and every sentence carries information about behavior or options. Dense colon-and-dash clause stacking makes the first sentence slower to parse than ideal, but there is 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?

Given an output schema exists and annotations cover safety, the description still supplies the behavioral details an agent needs: pre-filter syntax, handling of empty objectives, duplicate handling, crowding modes, and the ranking output columns. Nothing material for correct invocation 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 label, table, filter, maximise/minimise, crowding, and keep_duplicates in detail, including the same filter syntax example the description repeats. The description adds a little meaning (why crowding distance matters for spreading a short list) but does not compensate beyond the schema's baseline.

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+resource ('Pareto (non-dominated) sorting of rows scored on several columns, each to maximise or minimise') and frames the exact question the tool answers. The multi-objective ranking domain is distinctive enough to separate it from generic siblings like rank_strategies or summarize_rows without opening their schemas.

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 opening clause ('Which candidates ... are not beaten on every objective at once') gives clear context for when this tool applies, and the filter example shows the pre-filtering step. No explicit exclusions or named alternative tools are given, so it falls short of a 5.

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?