Jean — Molecular Biology & Genomics

scan_sigma70_promoters

Read-only

Find σ70 (housekeeping) promoters in a bacterial sequence and say how strong each one is, using the published La Fleur-Hossain-Salis biophysical model - six interaction motifs (UP element, -35, spacer, extended -10, -10, discriminator) plus the R-loop strength of the first transcribed bases, fitted on 22,132 characterised promoters.

Input Schema

Name	Required	Description
`_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.
`max_dg`	No	report only configurations at or below this ΔG_total. UNSET BY DEFAULT and deliberately so: this model publishes no significance cutoff, so the answer is a RANKING of the strongest configurations rather than a set of calls, and inventing a floor here is the exact defect the scanner this replaces had. Set it when you have a threshold of your own. In kcal/mol.
`_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.
`sequence`	No	the DNA to scan - leave unset to use the open record.
`region_end`	No	0-based inclusive end. Unset = the whole sequence. Advanced.
`max_results`	No	how many to return, strongest (most negative) first. Advanced.
`both_strands`	No	scan the reverse strand too. On by default: a cryptic promoter does not care which strand your insert was drawn on, and scanning one is how one gets missed.
`region_start`	No	0-based inclusive start of the region to scan. Unset = the whole sequence; pass the selection's start to scope to it. Advanced.

Output Schema

Name	Required	Description
`count`	Yes	how many are reported (`max_results`, or fewer if the sequence is short or `max_dg` was set)
`offset`	Yes	where the scanned stretch starts in the sequence: add it to every position above for sequence coordinates. 0 unless a region was given
`promoters`	Yes	the configurations, strongest (most negative) first, each with its six motif sequences, their positions and the per-motif energies that sum to its total
`strongest`	Yes	the most negative ΔG_total, or null when the sequence is too short to hold one
`strongestDg`	Yes	that hit's ΔG_total on its own, for a threshold downstream, or null when there is no hit

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already carry the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds genuine behavioural context beyond them: output is a strength ranking produced by a published biophysical model with six named motifs and an R-loop term, fitted on 22,132 promoters. It stops short of stating anything about limits of the model's applicability or how ties/short sequences are handled.

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?

A single front-loaded sentence that opens with the action and result before the model justification. It is dense but every clause (motifs, R-loop term, training-set size) supports trust in the score; the parenthetical motif list is the only mildly costly part.

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?

For a read-only scanner with a full output schema, complete parameter descriptions and explicit annotations, the remaining ambiguity is what the model is and whether scores are calls or rankings — and the description plus max_dg schema text answer both. Nothing an agent needs to invoke this correctly is missing.

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 all eight parameters including the nested _subject and _files are already documented in structured form. The description adds no parameter-level meaning of its own (e.g. how region windows interact with both_strands); the strongest parameter guidance, including the deliberate max_dg default, sits in the schema.

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 σ70 promoters in a bacterial sequence) plus the derived quantity (strength per site) and the exact model used. It is clearly distinguishable from neighbouring scanners such as scan_motif_sites, find_linear_motifs, or scan_intrinsic_terminators because it names the sigma factor and the biophysical model.

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 (housekeeping promoters in bacterial sequence, model-derived ranking) but never names an alternative tool or states when to prefer this over a generic motif scanner. Guidance about when-not-to-use and about the absence of a significance cutoff lives in the max_dg schema text rather than the description.

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?