Jean — Molecular Biology & Genomics

load_trace

Read-only

Read a Sanger trace (.ab1 / .scf / .ztr) from this project and hand its BASE CALLS onward as a record, with the per-base quality and the trim bounds beside them.

Input Schema

Name	Required	Description
`trim`	No	emit the quality-trimmed read rather than the whole call list. The bounds are the sliding-window mean-phred bounds the chromatogram panel trims by, so panel and pipeline cut at the same base.
`_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.
`document`	No	which trace file to read: its name (`read_F.ab1`) or its project file id. A file id is project-specific, so a template ships this unset.
`min_quality`	No	the mean phred a window must reach to be kept when trimming. Only applies when trim is true.
`reverse_complement`	No	read it on the other strand. A reverse primer's trace is the reverse complement of the strand you are verifying, and a name ending _R is the convention for it.

Output Schema

Name	Required	Description
`trace`	Yes	what the FILE says about itself: format, instrument comments, call count, trim bounds. Not the signal, which cannot ride a wire
`length`	Yes	how many bases that is
`record`	Yes	the read as a linear record, ready for any downstream step
`sequence`	Yes	its bases, trimmed when trimming is on
`ambiguous`	Yes	how many calls are not A, C, G or T: the mixed positions
`qualities`	Yes	per-base phred, parallel to the bases
`meanQuality`	Yes	the ARITHMETIC mean of the per-base phred, which is what FastQC plots. Always the higher of the two, because a phred score is a log of an error rate: keep it for comparison with other tools, gate on readQuality
`qualityPlot`	Yes	per-base phred as a plot along the read, with Q20 (1 error in 100) marked
`readQuality`	Yes	the read's own quality: the phred of its MEAN ERROR PROBABILITY, which is what seqkit's --avg-qual reports. Wire THIS into a gate to stop a bad read early
`expectedAccuracy`	Yes	the same number as a percentage of bases expected to be correct

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 25, 2026
- addedOutput schema / properties / expectedAccuracy / x-unit
```
Added value: +"%"
```
First observedOct 20, 2026

TDQS

B3.4/5.0

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, and the description is consistent with a local, non-mutating read ('from this project'). It adds the useful framing that the result is handed onward as a project record alongside quality and trim bounds, but it says nothing about failure behavior for a missing/unsupported file or how the trimmed vs untrimmed output differs beyond the trim bounds mention.

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?

One front-loaded sentence that leads with the action and ends with the delivered payload; no filler or restated title. It is arguably too compressed — a clause on when to choose it over sibling trace tools would cost little and earn its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With six parameters, nested _subject/_files objects and an output schema, the description covers the essentials (source scope, formats, what is returned) without needing to restate return values. What is missing is the relationship to neighbouring trace tools (call_bases_from_trace, trim_trace, export_trace, adopt_trace_calls), which an agent must resolve to select correctly.

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%, with rich per-parameter text for trim, min_quality, reverse_complement and document, so the schema carries the semantics. The description only alludes to trimming via 'the trim bounds beside them' and adds no detail on strand handling, quality thresholds, or how a trace is located by name versus project file id — 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 a Sanger trace (.ab1 / .scf / .ztr)') plus the payload produced ('BASE CALLS ... with the per-base quality and the trim bounds'). The explicit format list and 'from this project' scope make it distinguishable from list_traces or trace_raw_signal, but it never names the closest sibling (call_bases_from_trace) that an agent could confuse it with.

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 only implied: the agent infers it should be used when a trace file already exists in the project and base calls are wanted. There is no explicit 'use this when X, use Y instead' routing, no prerequisite statement, and no exclusion such as when to prefer calling bases fresh or pulling raw signal.

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?