Jean — Molecular Biology & Genomics

alignment_agreement

Read-only

Read an alignment window and say how well its reads agree with the reference underneath them, the way the pileup's own bar does: the compared and differing base counts, plus the RefSeq gene models and known dbSNP variants over the same window.

Input Schema

Name	Required	Description	Default
`locus`	No	the window, as a locus string (`chrM:3,300-3,460`). Unset, it is the whole of the alignment's first reference — the window the panel opens on.
`_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.
`variants`	No	also report the known dbSNP variants in the window. Off by default, as in the panel: it is a third layer over the reads and a dense window can hold thousands.
`alignment`	No	which BAM or SAM in this project, by name. Unset, it is the project's only alignment — and it refuses rather than guessing when there is more than one.
`reference`	No	what to compare against: a FASTA in this project by name, or a UCSC assembly id (`hg38`, `hg19`, `mm39` — the same list the panel's picker fetches). Unset is the panel's own default, No reference, and then only the window and its annotation are reported.
`gene_track`	No	which NCBI RefSeq set the gene models come from. Only meaningful against a UCSC assembly. The default is one curated transcript per protein-coding gene, which carries no mitochondrial genes at all — RefSeq Curated does. Values: ncbiRefSeqSelect (RefSeq Select and MANE), ncbiRefSeqCurated (RefSeq Curated), ncbiRefSeq (RefSeq All), ncbiRefSeqPredicted (RefSeq Predicted).	ncbiRefSeqSelect

Output Schema

Name	Required	Description
`rate`	Yes	differing aligned bases as a fraction of compared ones, 0 when nothing matched up
`genes`	Yes	the RefSeq models overlapping the window: symbol, accession, strand and bounds, as UCSC states them
`reads`	Yes	reads read for the window
`noCall`	Yes	aligned bases where one side is N — counted as neither, which is where this differs from an aligner's NM
`window`	Yes	the window actually measured, as a locus string
`cautions`	Yes	what this run earned: a reference whose length disagrees with the one the file declares, no-call bases counted as neither, and the window the numbers describe
`compared`	Yes	aligned bases that had a reference base to compare against — the denominator
`variants`	Yes	the dbSNP records in the window when asked for: rsID, alleles, class, highest reported frequency and ClinVar significance
`conclusion`	Yes	the reading in one sentence, generated from this run — the panel's own words
`mismatched`	Yes	of those, how many differ
`pathogenic`	Yes	how many of those ClinVar calls pathogenic

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 readOnly, non-destructive, closed-world, so the safety profile is covered. The description adds useful substance beyond that – it discloses the three output layers (agreement counts, RefSeq gene models, dbSNP variants) and the UI-parity intent. It does not mention that the tool refuses when the project holds more than one alignment, which is a notable behavioral trait left only to 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?

Effectively one front-loaded sentence that leads with the action and then enumerates the output layers. Dense but every clause carries information; nothing is redundant padding.

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, full schema description coverage, and read-only annotations, the description only needs to convey scope and intent, which it does. The main gap is sibling differentiation against alignment_window and compare_reads_to_reference, which would matter for selection.

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 every parameter (locus, alignment, reference, gene_track, variants, _subject, _files) is already richly documented, including defaults and refusals. The description adds no parameter-level meaning such as locus format examples or the significance of the gene_track choice, 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: read an alignment window and quantify how well the reads agree with the reference, reporting compared/differing base counts plus gene models and dbSNP variants. This distinguishes it from alignment_window and compare_reads_to_reference by the pileup-bar framing, though it never names those siblings explicitly.

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?

Usage is implied ('read an alignment window ... the way the pileup's own bar does') but there is no explicit when-to-use/when-not guidance and no named alternative among the many alignment siblings (alignment_window, compare_reads_to_reference, alignment_pca). The agent must infer routing from the description alone.

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?