Skip to main content
Glama

jean — Molecular Biology & Genomics

scan_intrinsic_terminators

Read-only

Find rho-independent (intrinsic) transcription terminators in a bacterial sequence: a stem-loop followed by a thymine-rich tail, scored by TransTermHP's published model (Kingsford, Ayanbule & Salzberg 2007). TWO NUMBERS, BOTH LOWER IS STRONGER - how well the hairpin folds and how thymine-rich the tail is - and NEITHER IS A FREE ENERGY: they are costs in this model's own scheme and must not be compared with a promoter's ΔG or a Turner ΔG. This is the question behind a downstream gene in an operon that goes quiet: a cryptic terminator inside an insert stops transcription that was meant to continue. Rho-DEPENDENT termination needs the protein and is not a sequence motif this or any such model can see. Reports every candidate clearing the two published cutoffs; TransTermHP itself lists one per position after its own overlap filters, so it reports fewer for the same sequence - a difference in reporting, not in scoring. No confidence value is given: TransTermHP's is a lookup into a table calibrated by its own GPL tooling, which is not shipped rather than approximated.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
_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.
_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.
sequenceNothe DNA to scan - leave unset to use the open record.
region_endNo0-based inclusive end. Unset = the whole sequence. Advanced.
max_resultsNohow many to return, best hairpin first. Advanced.
both_strandsNoscan the reverse strand too. On by default: a terminator on the strand you did not draw still stops transcription that runs into it.
region_startNo0-based inclusive start of the region to scan. Unset = the whole sequence; pass the selection's start to scope to it. Advanced.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countYeshow many are reported
offsetYeswhere the scanned stretch starts in the sequence: add it to every position above for sequence coordinates. 0 unless a region was given
strongestYesthe best-folding candidate, or null when none cleared both cutoffs
terminatorsYesthe candidates, best hairpin first, each with its stem-loop, its tail, the stem length and both scores
strongestHairpinYesthat candidate's hairpin score on its own, for a threshold downstream (lower is stronger). null when none cleared both cutoffs: there is no hairpin to score, and a 0 would pass a threshold as a measured value

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare a safe read-only, closed-world scan, but the description adds substantial context: the meaning and directionality of the two output numbers, an explicit warning that they are not free energies and must not be compared with promoter ΔG, and the reporting difference from TransTermHP's own overlap filters. It also explains why no confidence value is returned, which is exactly the kind of behavior an agent would otherwise misinfer.

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?

Purpose is front-loaded and the sentences carry real information rather than restating the schema. It is dense and long, with emphatic ALL-CAPS clauses and several defensive caveats, but each caveat guards against a plausible misinterpretation of the scores.

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 formatting needn't be described, and the description instead covers what matters: the semantics of the scores, the rho-dependent blind spot, and the reporting-vs-scoring distinction. For a 7-parameter scanning tool this is complete enough to call 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%, so every parameter (sequence, region_start/end, max_results, both_strands, _subject, _files) is already documented in the schema, including the 'best hairpin first' ordering and the both_strands rationale. The description text itself adds no further parameter-level detail, so the baseline 3 applies.

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 ('Find rho-independent (intrinsic) transcription terminators'), defines the motif concretely (stem-loop plus thymine-rich tail), and cites the scoring model. It also draws a hard boundary against rho-dependent termination, so an agent can distinguish it from the other scan_* siblings 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 Guidelines4/5

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

Gives a clear motivating scenario ('the question behind a downstream gene in an operon that goes quiet') and states the case it cannot handle (rho-dependent termination). However, it never names or routes to a sibling tool (e.g. scan_sigma70_promoters, fold_rna), so the when-to-use guidance is contextual rather than comparative.

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