jean — Molecular Biology & Genomics

design_oligo_plate_order

Read-only

Lay a set of oligos out as a supplier's PLATE order sheet: one worksheet per plate, in the well order the supplier's own order form fills, with the column shape its loading direction requires. A plate order is addressed BY WELL, which a flat tube list cannot express — so this is the shape an oligo set actually gets ordered in once it outgrows a handful of tubes. With mixed, a forward and a reverse share one well, which is what the supplier's doubled mix-plate layouts encode. It WRITES A FILE and sends nothing: no account, no key, no network call.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`fill`	No	how the plate is loaded. It decides the FILE'S COLUMNS, not just the order: a plate filled by row or by column carries no well column at all, because the supplier derives each position from the row order. Values: rows (Rows (A1, A2, A3 …)), columns (Columns (A1, B1, C1 …)), explicit (Explicitly entered).	rows
`mixed`	No	one well per PRIMER PAIR: `oligos` is read as forward, reverse, forward, reverse, and each plate is written as every well once carrying the forwards and again carrying the reverses.
`names`	Yes	a name per oligo, in the same order. A plate well is ORDERED BY NAME, so an unnamed oligo is refused rather than numbered: the label is what the supplier ships the tube under.
`_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.
`format`	No	wells per plate. Values: 96 (96 well), 384 (384 well).
`oligos`	Yes	the oligos to lay out, 5'→3'. Wire them from a design run, or list them. With `mixed`, these are read in FORWARD, REVERSE order — two entries per well.
`_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.
`plate_name`	No	the plate's name, which becomes the worksheet's name. Several plates get ' (2)', ' (3)' appended.	Plate 1
`pad_to_capacity`	No	write every unused well as the supplier's blank-name, blank-sequence row rather than ending the sheet short. Advanced.

Output Schema

TableJSON Schema

Name	Required	Description
`tsv`	Yes	the FIRST plate as tab-delimited text, in the column shape the loading direction requires — the shape the supplier's own paste box accepts verbatim. Several plates means several sheets: read `sheets` for the rest
`sheets`	Yes	one entry per PLATE: its name, its grid, how many wells it fills against the plate's capacity, and every laid-out well
`columns`	Yes	the header row this order was written with, which is the two-vs-three column rule the loading direction decided
`reading`	Yes	what the order is, generated from the laid-out plates rather than from the request
`refused`	Yes	every oligo left OUT, with the reason. Never empty-because-nothing-was-checked: an order that is quietly short is one the user pays a supplier for
`wellNote`	Yes	why the well labels are written unpadded, which is a collision in the supplier's own form rather than our choice
`plateCount`	Yes	how many plates the set needed. Branch a workflow on this rather than re-deriving it

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

B3.4/5.0

Behavior1/5

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

The description states 'It WRITES A FILE', which directly contradicts readOnlyHint=true (a read-only tool does not modify its environment). This is an annotation contradiction. Other details such as no network, no account, and no key align with openWorldHint=false and destructiveHint=false, but they do not resolve the core inconsistency.

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?

Front-loaded with the core action, then rationale, then key parameter behavior, then the file-writing caveat. Four sentences are somewhat dense but each carries purpose, context, or behavior; there is no redundant filler.

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 complex 9-parameter design tool with nested objects and an output schema, the description covers purpose, ordering context, key parameter behavior, and the output side effect. It leaves minor parameters to schema descriptions, which is acceptable given full schema coverage and output schema presence.

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 description coverage is 100%, so the baseline is 3. The description adds semantic depth beyond the schema: it explains that `mixed` makes a forward and reverse share one well and that `fill` determines the file's columns and loading direction.

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?

States a specific verb (Lay out) and resource (oligos as a supplier's PLATE order sheet), including the output structure of one worksheet per plate and well-order loading. It distinguishes from a flat tube list, but does not name a competing sibling tool, so it is clear without full sibling differentiation.

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?

Gives clear context: use when an oligo set outgrows a handful of tubes and must be ordered by well, which a flat tube list cannot express. It lacks explicit exclusions or named alternative tools, but the when-to-use scenario is unambiguous.

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?