Jean by Melad Labs

run_gel_plate

Read-only

Run a multi-lane virtual agarose gel and return its READING, not just its bands: how many lanes carrying how many bands over what range, positioned by which ladder, plus only the cautions this plate earned — a lane running off the top or bottom of the reference ladder entirely (no mark to interpolate against, so the position is the calibration curve extrapolated), a band inside the ladder but outside the resolving window of the agarose percentage cast, two fragments co-migrating as one drawn band, a DNA form the chosen law cannot move, an empty lane, and a refused calibration.

Input Schema

Name	Required	Description	Default
`form`	No	the DNA topology a lane runs at when its bands do not carry one. Only moves a band under a concentration law: ladder-calibrated migration reads every band off the ladder's own curve, and the reading says so rather than leaving the setting silently inert. Advanced.	linear
`lanes`	Yes	the lanes, in edge order — each a `[bp, form]` band list, which is exactly what `run_gel_lane` emits. A bare list of fragment lengths is also accepted and runs at the plate `form`. Several wires land here.
`_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.
`ladder`	No	the reference ladder drawn beside the samples, and what "off the scale" is measured against. Values: generuler_1kb_plus (GeneRuler 1 kb Plus (75–20,000)), hi_lo (Hi-Lo DNA Marker (50–10,000)), generuler_1kb (GeneRuler 1 kb (250–10,000)), generuler_100bp (GeneRuler 100 bp (100–3,000)), generuler_100bp_plus (GeneRuler 100 bp Plus (100–3,000)), thermo_1kb_plus (Thermo 1 Kb Plus (100–15,000)), neb_1kb (NEB 1 kb (500–10,000)), neb_100bp (NEB 100 bp (100–1,517)), lambda_hindiii (Lambda DNA / HindIII (125–23,130)), penn_state (PennState (500–10,000)).	generuler_1kb_plus
`_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.
`lane_names`	No	a name per lane, in the same order. Unnamed lanes become `Lane 1`, `Lane 2`, … — the reading names the lane every caution is about, so a plate of unnamed lanes still says which one is off scale.
`render_mode`	No	how the plate would be drawn. Echoed into the derivation chain because a raster merges what bands separate, so the reading is about a different picture. Advanced.	bands
`mobility_model`	No	which empirical agarose-% mobility law — helling-goodman-boyer (Helling–Goodman–Boyer (default)) · rill-van-winkle (Rill/Van Winkle). Values: helling-goodman-boyer (Helling–Goodman–Boyer (default)), rill-van-winkle (Rill/Van Winkle). Only applies when agarose_percent is set. Advanced.	helling-goodman-boyer
`agarose_percent`	No	the casting percentage, which activates a concentration law and a resolving window. LEAVE UNSET for the bench's own default: ladder-calibrated migration, interpolated on the ladder's measured curve with no concentration term. In %.

Output Schema

Name	Required	Description
`bands`	Yes	every placed band: lane, length in bp, Rf and migration on the shared coordinate system, and whether this gel can measure it
`cautions`	Yes	only the cautions this plate earned, each carrying the measurement that produced it and naming the lane it is about. Empty when every band is measurable
`conclusion`	Yes	the one-sentence reading, generated from this run: lanes, bands, the size range they span, and the ladder that positioned them
`derivation`	Yes	the machinery, one row per fact: what placed the lanes, the ladder that calibrated them and whether its curve is its own or borrowed, the resolving window, each lane`s DNA form, and how the plate is drawn
`calibratedBy`	Yes	the ladder whose measured curve positioned every lane — which is NOT always the ladder drawn: 2 of the 10 built-ins carry (bp, Rf) points, and a gel showing one of the other 8 is positioned on the default curve
`unmeasurable`	Yes	per lane, the two failures kept apart because different actions fix them: `offScale` (outside the reference ladder entirely — read it off the table) and `outOfWindow` (inside the ladder, outside this percentage`s resolving range — cast a different gel)

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

B3.4/5.0

Behavior4/5

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

Annotations already declare this a non-destructive, closed-world read, and the description adds substantial context beyond that: it specifies the reading contents (lane count, band count, range, ladder basis) and enumerates the exact caution classes the tool will emit, including the noteworthy 'refused calibration' failure mode and the extrapolation caveat for off-ladder lanes. It stops short of saying whether the reading is deterministic across repeated calls or how a partially failed plate behaves, so it is rich but not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The key claim is correctly front-loaded in the first clause, but the rest is a single ~90-word sentence stitched with em-dashes and a comma-separated caution inventory, which makes it hard to parse quickly. The caution enumeration carries real information, but the 'not just its bands' framing and the parenthetical definitions could be tightened considerably.

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 9-parameter tool with a nested `_subject` object and an output schema, the description covers the conceptual model (ladder calibration, concentration law, resolving window, co-migration) that an agent needs to interpret results. Gaps remain around how `lanes` entries relate to `run_gel_lane` output at the description level, and how this tool differs from `draw_gel`, but the output schema carries return-value detail.

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 itself already explains form, ladder, lane_names, render_mode, mobility_model and agarose_percent. The description only adds the high-level framing that ladder choice determines 'positioned by which ladder' and that the reading is a calibration-based measurement, which is marginal beyond the structured fields; 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?

The opening clause names a specific verb and resource ('Run a multi-lane virtual agarose gel') and immediately scopes the output ('return its READING, not just its bands'), so an agent knows this is a simulated plate reading rather than a drawing. It is weaker at distinguishing from siblings: the single-lane `run_gel_lane` is only cross-referenced inside the schema text, and the relationship to `draw_gel` (which plausibly renders a gel image) is never addressed, so the agent must infer which of the two produces a picture.

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 statement, no prerequisites, and no named alternative in the description body. Usage is only inferable from the adjective 'multi-lane' and the fact that the caution list presumes a calibration setup.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Jean by Melad Labs 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?