Skip to main content
Glama

debarcode_mass_cytometry

Read-only

CATALYST single-cell debarcoding of a barcoded mass cytometry FCS file in the project, with a barcoding key (a CSV: barcode id, then one 0/1 column per barcode mass): each event's barcode from the order of its asinh-transformed barcode channels, the channels scaled per barcode by the 95th percentile of its positive values, events whose separation is below the cutoff (one for every barcode, or each barcode's own estimated from its yield curve, estCutoffs) or whose Mahalanobis distance from their barcode's population exceeds the cutoff unassigned; per-barcode yields.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "debarcode_mass_cytometry"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNothe barcoding key CSV in the project, by name or id; empty when the project holds one.
_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.
gatingNoa Gating-ML or FlowJo .wsp in the project; empty for none.
derivedNoas analyze_flow_cytometry.
_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.
documentNothe FCS file in the project, by name or id.
mhl_cutoffNothe Mahalanobis distance beyond which an event is unassigned; CATALYST's 30.
sep_cutoffNothe separation below which an event is unassigned; 0.35 is CATALYST's example.
compensationNoas analyze_flow_cytometry.auto
barcode_cofactorNobarcode intensities read as asinh(x / barcode_cofactor); CATALYST's 5.
estimate_cutoffsNoestimate each barcode's separation cutoff from its yield curve (CATALYST estCutoffs: a three-parameter log-logistic and a linear fit, weighted by their residuals) instead of sep_cutoff.
compensation_methodNoas analyze_flow_cytometry.flowkit

Output Schema

NameRequiredDescriptionDefault
yieldsYesper barcode: events assigned before and after the cutoffs, and the cutoff used (estimated or given)
unassignedYesevents left unassigned

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / estimate_cutoffs
      Added value: +{
      +  "default": false,
      +  "description": "estimate each barcode's separation cutoff from its yield curve (CATALYST estCutoffs: a three-parameter log-logistic and a linear fit, weighted by their residuals) instead of sep_cutoff.",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / yields / description
      Previous value: -"per barcode: events assigned before and after the cutoffs, and the cutoff used"New value: +"per barcode: events assigned before and after the cutoffs, and the cutoff used (estimated or given)"
  2. Added

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare this a read-only, non-destructive, closed-world operation, and the description goes well beyond that by disclosing the actual algorithm: per-channel asinh transform, per-barcode 95th-percentile scaling, and the two conditions (separation cutoff, Mahalanobis distance) that cause events to be left unassigned. It also notes the per-barcode yield output. It stops short of describing failure modes, but the behavioral picture is unusually rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, but the body is a single long run-on sentence stitched together with colons and semicolons, making it dense to parse. Little is wasted, yet the algorithmic detail could have been broken into shorter, scannable clauses.

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 tool with nested objects and an output schema, the description covers the core behavior, the barcoding-key format, and the cutoff logic that an agent needs to invoke it correctly. Parameters such as compensation, derived, and gating are delegated to 'as analyze_flow_cytometry', which is an acceptable shortcut given the sibling tool exists.

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 is already documented, which sets the baseline at 3. The description reinforces the meaning of sep_cutoff, mhl_cutoff, barcode_cofactor and estimate_cutoffs and clarifies that estimated cutoffs come from each barcode's yield curve, but most of this restates what the schema already says rather than adding new semantics.

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?

The description names a specific verb (CATALYST single-cell debarcoding) and resource (a barcoded mass cytometry FCS file in the project), so the operation is unmistakable. It does not explicitly contrast itself with the many flow-cytometry siblings, but 'debarcoding' is distinctive enough that an agent can separate it from analyze_flow_cytometry or auto_gate_flow_cytometry.

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: you bring a barcoded FCS file plus a barcoding-key CSV, and the description explains what the key looks like. There is no explicit when-to-use/when-not statement and no sibling alternative is named, leaving the agent to infer that this is the debarcoding step rather than a general analysis step.

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