Jean — Molecular Biology & Genomics

scan_splice_sites

Read-only

Find the splice sites a sequence accidentally spells - the check a codon-optimised CDS needs before it goes into a plant or any other eukaryotic host, because a synonymous swap chosen for codon usage or GC can spell a donor or acceptor that was not there before, and the transcript is then spliced somewhere nobody intended.

Input Schema

Name	Required	Description	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.
`strand`	No	which strand to read. Both by default: an antisense site still splices a transcript made from the other strand, and in a construct both may be transcribed. Name the gene's own strand when you know it, and the other strand's candidates stop crowding the ranking.	both
`_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.
`sequence`	No	the DNA to scan - leave unset to use the open record.
`min_maxent`	No	report only sites at or above this MaxEntScan score, in bits. UNSET BY DEFAULT and deliberately so - MaxEntScan publishes no significance cutoff and the measured matrices are a description rather than a classifier, so a default here would be a decision boundary nobody has published. Set it when you have a threshold of your own. In bits.
`max_results`	No	how many to return, strongest first. Advanced.

Output Schema

Name	Required	Description
`count`	Yes	how many are reported
`sites`	Yes	the candidates, strongest MaxEnt first, each with its kind, position on the strand you passed, the window that was scored, and both scores
`strongest`	Yes	the highest-scoring candidate, or null when the sequence is too short to hold a window
`strongestMaxEnt`	Yes	that candidate's MaxEntScan score on its own, for a comparison downstream, or null when there is no candidate: 0 is a real MaxEntScan score

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A3.6/5.0

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 the safety profile is covered. The description adds genuine domain context about the failure mode being detected (cryptic donor/acceptor created by synonymous swaps), but says nothing about the scoring model, ranking, or what an unset threshold yields — details that live only in the schema.

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 in the first clause, and the trailing 'because' chain justifies the tool rather than restating it. It is a single long run-on sentence with some flourish ('somewhere nobody intended'), but no sentence is 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?

With an output schema present and full schema coverage, the description only needs to establish what the tool looks for and why; it does that convincingly. The one gap is that it never hints the tool reports scored, ranked candidate sites rather than a simple yes/no, which matters for interpreting results.

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 schema itself is unusually rich (min_maxent explains the absence of a default, strand explains both-strand behaviour, _subject enumerates record sources). The description adds no parameter-level meaning at all, 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?

States a specific verb and resource ('Find the splice sites a sequence accidentally spells'), and the 'accidentally spells' framing separates it from deliberate-motif scanners like scan_motif_sites and from scan_intrinsic_terminators/scan_sigma70_promoters by naming the eukaryotic splice-donor/acceptor target. It does not name a sibling explicitly, so it stops short of a 5.

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 a clear triggering situation: run it on a codon-optimised CDS before the construct goes into a plant or other eukaryotic host. That is actionable context, but there are no exclusions or pointers to alternatives (e.g. motif scans or terminator/promoter scanners) for agents deciding between the many scan_* 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?