Skip to main content
Glama

Sequencing read-back verification

sequencing_readback_verify
Read-onlyIdempotent

Align raw Sanger or NGS reads (FASTA or FASTQ) back onto a claimed reference sequence using minimap2, and report per-read mapping identity plus exact variant positions (substitutions/insertions/deletions), with a consensus view across reads and a corrected consensus sequence (the reference with every consensus-supported edit applied). Each alignment also reports how much of the READ was used (queryCoveragePct/clippedBases), since identity is measured over the aligned portion only and a partially-used read would otherwise score perfectly. Set circular: true for a plasmid so reads crossing the reference's arbitrary linear start are aligned through the join rather than cut short at it. Also calls STRUCTURAL variants from split alignments — a large deletion, tandem duplication, inversion or backbone rearrangement never appears as a run of mismatches, only as one read aligning at several distant reference positions, so per-base calling reports a perfect clone — and returns a coverage depth profile with the regions no read reached at all, since "never read" is not "correct". On a circular reference one junction cannot always tell an event of length d from one of length referenceLength − d the other way round; where the read's own blocks and the coverage profile settle it they do, and where they do not the call carries an alternateInterpretation with the other reading rather than presenting one as a finding. Set platform (nanopore/pacbio/illumina/sanger) to pick minimap2's preset; the preset used is reported back. Complements verify_construct/verify_assembly: those re-derive what a design SHOULD produce from its own stated inputs; this checks what a real sequencer actually read back.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
readsYesRaw reads in FASTA or FASTQ format (auto-detected). Up to 2000 reads / 5,000,000 total bp per call.
circularNoTreat the reference as a circular molecule (plasmid). Reads that straddle its arbitrary linear start are then aligned right through the join instead of being cut short there, so variants in the part that would otherwise be clipped away are actually called. Turn this on for whole-plasmid data — the reads begin wherever the molecule was cut, so most of them cross the join. Reads longer than the reference still get clipped. It also governs structural-variant calling: on a circle an origin-crossing read is contiguous, and only this flag lets it be told apart from a whole-reference duplication.
platformNoRead type, which selects minimap2's alignment preset. "auto" (the default) passes no preset and uses minimap2's own defaults — whose parameters happen to be map-ont's, so nanopore data is already handled; setting "nanopore" makes that explicit and pins it. "pacbio" uses map-hifi and "illumina" uses sr, both of which materially change the result: under the ONT defaults gaps are cheap, so on accurate reads a cluster of mismatches can be reported as a spurious indel. "sanger" uses map-hifi with the minimum alignment score returned to 80, because map-hifi's own floor of 200 was chosen for 10-25 kb reads and would leave a short or partly-failed Sanger read unmapped. The preset actually used is reported back as minimap2Preset/alignerArgs so a run can be reproduced. Names are matched ignoring case and punctuation, and the obvious aliases resolve ("ONT" and "map-ont" to nanopore, "HiFi" to pacbio, "sr" to illumina); anything unrecognised is rejected rather than silently treated as "auto".auto
referenceYesThe claimed/expected reference sequence.
minSvLengthNoSmallest structural variant to report, in bp (default 50). Below this the per-base variant caller already reports the event from inside a single alignment, and on nanopore data the range is mostly the error profile.
minSvSupportNoDistinct reads that must agree on the same breakpoint before a structural variant (large deletion, duplication, inversion, insertion) is reported. Default 3 — stricter than minSupportingReads on purpose: a single split read is a library-prep chimera or a mapping artefact far more often than it is biology, and chimeras are common enough that two agreeing by chance is likelier than two matching base errors.
minSupportingReadsNoMinimum number of reads agreeing on a variant position for it to count as a consensus (candidate real) variant rather than single-read noise.
breakpointToleranceNoHow far apart two reads' breakpoints may sit and still count as the same event, in bp (default 50). Long-read breakpoints are fuzzy, and microhomology at a real junction moves the split legitimately.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already indicate readOnlyHint and idempotentHint, and the description adds substantial behavioral nuance beyond that: identity is measured over aligned portion only, split alignments are needed for structural variants, unread regions are reported as 'never read' rather than correct, and circular-reference ambiguity yields alternateInterpretation rather than a single finding. No contradiction with annotations.

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?

The description is dense and front-loaded with the core purpose, and every section earns its place by conveying behavior not available in the schema. It is longer than strictly necessary, but the tool is complex and the extra length is mostly justified by important caveats about circular references, split alignments, coverage, and platform presets.

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?

There is no output schema, so the description carries the burden of explaining return values, and it does: per-read mapping identity, exact variant positions, consensus view, corrected consensus, queryCoveragePct/clippedBases, coverage depth profile, alternateInterpretation, and minimap2Preset/alignerArgs. With 8 parameters and no output schema, the description is sufficiently complete for an agent to select and invoke the tool 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 description coverage is 100%, so the baseline is 3. The description adds genuine semantic value beyond the schema by explaining why minSvSupport defaults stricter than minSupportingReads, why platform choice matters for gap penalties, and why circular mode affects both alignment and structural-variant interpretation. It does not simply restate parameter names or types.

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?

The description opens with a specific verb and resource: aligning raw Sanger/NGS reads back onto a claimed reference using minimap2, and enumerates concrete outputs (per-read identity, exact variant positions, consensus view, corrected consensus). It also differentiates itself from verify_construct/verify_assembly by stating that this tool checks real sequencer output rather than re-deriving expected design output.

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?

The description explicitly names the sibling tools it complements and states what they do versus what this tool does. It also gives concrete usage guidance, such as setting circular: true for plasmids so reads crossing the linear start are aligned through the join, and selecting platform to pick minimap2's preset.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation4/5

Most tools have highly specific purposes (e.g., crispr_grna_design vs base_editing_design vs prime_editing_design). However, there is some overlap in sequence analysis tools (characterize_sequence, sequence_report) and plasmid annotation tools (plasmid_annotate vs plasmid_deep_annotate) which could cause confusion.

Naming Consistency3/5

The naming pattern is largely consistent with snake_case verb_noun or noun_descriptor (e.g., primer_design, plasmid_annotate, fastq_trim). However, there are exceptions like 'batch', 'workflow', 'gc_content', and 'cloning_diagnose' which don't follow the verb_noun pattern consistently. Also, some names are phrases like 'golden_gate_from_parts'.

Tool Count2/5

With 101 tools, this server is extremely large and likely overwhelming for agents. Even for a comprehensive bioinformatics toolkit, this exceeds a manageable scope, risking agent confusion and inefficient tool selection. A more modular approach would be advisable.

Completeness4/5

The tool surface covers a wide range of bioinformatics workflows including sequence analysis, primer design, cloning, CRISPR, NGS, expression analysis, and data export. There are minor gaps such as lack of a dedicated protein structure prediction tool and limited off-target genome coverage, but overall the set is impressively complete for its domain.

Resources