jean — Molecular Biology & Genomics

apply_feature_file

Put the features from a GTF in this project onto the open record. A GTF lists features and their positions and carries no sequence, so this is how one reaches a molecule. It REFUSES unless something says the two are in the same coordinate space: if the file names a genome build and the record names the same one it proceeds; if they name different ones it refuses outright; if either is silent it refuses until you pass coordinates_only, which states that you are applying the intervals as positions in this record's own numbering with no genome correspondence checked. Reports what would not fit rather than trimming it.

Input Schema

TableJSON Schema

Name	Required	Description
`file`	No	the annotation file in this project, by name. Unset with exactly one present uses it; with several, this refuses and names them rather than picking.
`_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.
`_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 seqid within the file whose features to apply (a GTF names one per row). Unset with exactly one present uses it; with several, this refuses and names them — applying the wrong chromosome's intervals is the mistake this parameter exists to prevent.
`coordinates_only`	No	state that you are applying the intervals as COORDINATES — positions in this record’s own numbering — with no genome correspondence checked. Applying coordinates on that basis is a claim about your own data, and the run records it as the basis it used. Required whenever either side is silent about its assembly; it cannot rescue two assemblies that disagree.

Output Schema

TableJSON Schema

Name	Required	Description
`added`	Yes	how many features were written — branch on this rather than counting
`basis`	Yes	what earned the apply: 'matched' when both assemblies agreed, 'coordinate-space-only' when you stated it. A run's provenance, not a status
`record`	Yes	the open record with the applied features added
`duplicate`	Yes	how many were already on the record at the same span, strand and type, so they were not written twice
`outOfRange`	Yes	the features whose spans run past the end of the record, each with the end it really has. Reported, never trimmed: a span cut to fit is a different feature

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, but the description adds genuinely non-derivable behavior: the coordinate-space gate, the special coordinates_only basis recording, and the fact that it reports non-fitting features instead of trimming. It stops short of describing exactly how the open record is mutated or what the report looks like, so a 4 rather than 5.

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?

Five sentences, front-loaded with the core action and then the refusal rules; each sentence carries substantive information rather than filler. It is slightly dense/long, but no sentence is redundant for a tool with this much gating logic.

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?

An output schema exists so return values needn't be explained, and annotations cover the safety profile. For a 5-parameter tool with nested objects, the description supplies the decisive coordinate-space contract and overflow behavior, leaving nothing an agent needs in order to call it correctly.

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 coverage is 100%, so the baseline is 3, but the description synthesizes the interplay the schema documents piecemeal: file/sequence disambiguation ('with several, this refuses and names them') and the conditional requirement logic for coordinates_only. It clarifies intent (avoid applying the wrong chromosome's intervals) beyond the raw field descriptions.

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 and resource ('Put the features from a GTF ... onto the open record') and immediately clarifies why the operation is needed ('a GTF carries no sequence, so this is how one reaches a molecule'). An agent can distinguish this from siblings like annotate_region or load_record without opening a schema.

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

Usage Guidelines5/5

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

Gives explicit proceed/refuse conditions: proceeds when both sides name the same genome build, refuses outright when they name different ones, and refuses when either is silent unless coordinates_only is passed. This is an unambiguous when-to-use rule plus the escape hatch, with no reliance on inference.

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?