Skip to main content
Glama

jean — Molecular Biology & Genomics

ligate_fragments

Ligate fragments by their overhangs (pydna ligation_assembly) — sticky, optionally blunt. Each input may be digested by its own enzymes first, which is the digest → ligate hand-off. Emits the first product as a NEW record.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bluntNoallow blunt-end joins as well as sticky.
_filesNoThe 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.
enzymesNodigest every input with these enzymes before ligating. Left unset, the run uses your active enzyme collection.
fill_inNopositional booleans: fill that input's 5' overhangs with Klenow after its digest, so its cut ends join blunt (needs `blunt`). Each join then reports the bases the fill-in added. Advanced.
_subjectNoThe 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.
fragmentsNothe fragments to ligate — wire upstream `record` outputs here, or name library documents.
end_originsNowhat MADE each input's ends, positionally — this fixes the 5'-phosphate before any treatment. Leave empty for `unspecified`, which is treated as phosphorylated and reproduces a run with no end chemistry at all. Advanced.
circular_onlyNoreport only circular products.
end_treatmentsNothe phosphatase or kinase applied to each input AFTER it was made, positionally. Dephosphorylating the vector is what stops it self-ligating; a junction with no 5'-phosphate on either strand forms no bond and the product is dropped. Advanced.
include_subjectNoalso include the node's subject as a fragment.
fragment_indicesNowhich band to take from each input's digest, positionally (0 = first fragment). Leave empty to use every fragment — which frequently yields no product, exactly as at the bench.
allow_partial_overlapNoallow partially overlapping sticky ends. Advanced.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
layoutYeswhere each piece and join sits ON the product: the spans the map draws
recordYesthe first ligation product, as a record
productsYesevery product
junctionsYesthe junctions formed, with the overhang each was made by
productCountYesnumber of products (>1 = ambiguous ligation)
nickedJunctionsYesindices of junctions left NICKED by a missing 5'-phosphate on one strand — the product still transforms and is repaired in vivo. Empty when every junction sealed

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly=false, destructiveHint=false and openWorld=false, so the mutation/safety profile is partly covered. The description adds genuine value by stating the digest→ligate hand-off behavior and that it 'emits the first product as a NEW record', clarifying output cardinality and that inputs are untouched.

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?

Three compact sentences with the core ligation action front-loaded, then the digest hand-off, then the output. No filler, though the parenthetical '(pydna ligation_assembly)' and 'NEW record' emphasis are slightly redundant.

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?

For a 12-parameter advanced tool, the description covers the essential mental model (overhangs, per-input digestion, new-record output) and an output schema plus 100%-covered params carry the rest. It could say more about the pipeline defaults (e.g. circular_only) but is largely complete.

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 the schema already documents all 12 parameters, including the advanced ones (fill_in, end_treatments, end_origins). The description reinforces the overhang/blunt concept and the digest-first behavior but adds no syntax or format detail beyond the schema, 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+resource (ligate fragments) and the mechanism (overhang-based ligation, sticky/optionally blunt, pydna ligation_assembly). It is clear what the tool does, but it does not explicitly differentiate itself from close siblings such as restriction_ligate, gibson_assemble, or golden_gate_assemble.

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?

The description implies usage through the 'digest → ligate hand-off' framing, telling the agent this follows a digest step and can fold per-input digestion into the run. However, it gives no explicit when-to-use/when-not guidance and never names an alternative assembly tool (Gibson, Golden Gate) to route between.

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.

Resources