Jean — Molecular Biology & Genomics

design_free_codes

Read-only

Generate INDEL-correcting barcodes — FREE divergence codes (Hawkins et al., PNAS 2018) — by reserving each codeword's error sphere over the whole 4^k space, so the guarantee survives an insertion or deletion rather than only a substitution.

Input Schema

Name	Required	Description	Default
`mode`	No	generate a new code, or prune an existing set down to a valid one. Values: generate (Generate a code), prune (Prune a set to a valid code).	generate
`limit`	No	stop after this many codewords. 0 = take the whole code. 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.
`length`	No	barcode length k. The search is over the whole 4^k space, so cost rises steeply with it.
`max_gc`	No	reject a candidate above this GC fraction. 0 = no limit. Advanced.
`_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.
`barcodes`	No	the set to prune — required when `mode` is `prune`, ignored when generating. Only applies when mode is prune.
`reserved`	No	codewords already in use, whose decode spheres are claimed BEFORE generation — this is how a code is EXTENDED rather than regenerated, so what comes back is compatible with the indexes a lab already owns.
`max_errors`	No	how many insertions/deletions/substitutions each codeword must tolerate. Each extra error costs most of the code.
`max_homopolymer`	No	reject a candidate with a run of this many identical bases. 0 = no limit. Advanced.

Output Schema

Name	Required	Description
`count`	Yes	how many codewords came back
`dropped`	Yes	prune only: the codewords removed because their decode spheres collided — a user pruning their own set needs to know which indexes to stop using, not how many
`barcodes`	Yes	the codewords — generated, or the ones that survived pruning

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered by structured data. The description adds genuine mechanism context — error spheres reserved over the whole 4^k space, guarantee holding for indels — but says nothing about runtime, determinism, or the cost of raising max_errors, all of which matter for a search-based generator.

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?

A single front-loaded sentence that leads with verb+resource and then motivates the design. It is dense with jargon and an em-dash citation aside, but nothing is redundant.

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 10 parameters, a nested _subject object, full schema coverage and an output schema, the definition's remaining burden is purpose and mechanism, which it delivers. The one real gap is sibling routing — nothing tells the agent to prefer this over design_barcodes or design_codehop.

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% and the parameter docs are unusually rich (reserved, max_errors, barcodes/mode interaction all explained in-schema). The description adds only the conceptual framing of the search space, not new parameter-level meaning, 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?

The description pairs a specific verb (generate) with a specific resource (INDEL-correcting barcodes / FREE divergence codes, with a literature citation) and adds 'rather than only a substitution', which implicitly separates it from substitution-only barcode design. It never names a sibling tool (design_barcodes, design_codehop, design_degenerate_primers) outright, so the differentiation is inferential rather than explicit.

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

Usage Guidelines3/5

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

Use is only implied: an agent can infer it should pick this when a code must survive insertions/deletions. There is no stated when-not, no prerequisites, no mention of the generate-vs-prune workflow (that lives only in the schema), and no routing to the other barcode-design siblings.

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?