Skip to main content
Glama

batch_flow_cytometry

Read-only

One strategy, compensation and scale over many project FCS files: each population's count and % per sample (samples it cannot gate listed with the reason); with a sample sheet column, populations compared between groups (Welch t, Kruskal-Wallis, Welch one-way ANOVA) or by two columns (two-way ANOVA, R aov).

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": "batch_flow_cytometry"
  }
}

Input 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.
and_byNoa second sample-sheet column: each population's percentage by both columns at once, R summary(aov()) with sequential sums of squares (group_by first); empty for none.
gatingNoa Gating-ML or FlowJo .wsp in the project; empty for none.
derivedNoas analyze_flow_cytometry.
measureNowhich percentage is compared. Values: percentOfParent (% of parent), percentOfTotal (% of total).percentOfParent
samplesNothe FCS files to run, by name or id, comma-separated; empty for every FCS file in the project.
_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.
group_byNothe sample sheet's column whose values are the groups to compare.
concordanceNoa one-dimensional range gate of the strategy to compare, sample by sample, with openCyto's automated cut (gate_mindensity) on the same parent and channel, scored by Lin's concordance correlation; empty for none.
interactionNowith and_by, also fit the two columns' interaction (y ~ A * B).
compensationNoas analyze_flow_cytometry.auto
sample_sheetNoa CSV in the project whose first column, headed sample, names each FCS file; empty for no groups.
compensation_methodNoas analyze_flow_cytometry.flowkit

Output Schema

NameRequiredDescriptionDefault
tableYespopulations × samples: counts, % of parent, % of total, and the samples refused
two_wayYesper population: the two-way ANOVA table (df, sum of squares, mean square, F, p per term and the residuals), or why none
comparisonsYesper population: the groups, their means and the tests
concordanceYesper sample the manual and automated % of parent and the cut, and Lin's concordance correlation with its 95% interval, scale and location shifts and bias-correction factor

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

The annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so safety is covered. Beyond that, the description discloses a genuine behavioral trait: samples that cannot be gated are reported with a reason rather than silently dropped. It also names the exact statistical tests (Welch t, Kruskal-Wallis, Welch one-way ANOVA, two-way ANOVA via R aov), but says nothing about runtime or scale on large batches.

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?

Two dense semicolon-separated clauses, front-loaded with the scope of the batch operation before the outputs and the optional stats. Every clause carries content, no filler, but the phrasing is compressed enough that the sample-sheet-to-comparison logic takes a second read.

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 14-parameter tool with nested record objects, this covers the primary outputs, failure reporting and group-comparison modes, and an output schema exists so return shape needs no explanation. The only gap is that several analysis-shaping parameters are only cross-referenced to a sibling tool.

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 coverage is 100%, so the schema carries the baseline, and the description still adds real meaning: how sample_sheet, group_by and and_by compose into the comparisons, and that a two-column split yields a two-way ANOVA with an optional interaction term. Other parameters (gating, derived, compensation, concordance) are defer to 'as analyze_flow_cytometry' or left to the schema, which is acceptable given full coverage.

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 states a specific verb and resource combination: applying one gating strategy, plus compensation and scale, across many project FCS files, producing per-population counts and percentages and group comparisons. The 'many project FCS files' scope is what separates it from single-sample analysis. It doesn't name analyze_flow_cytometry as the single-sample alternative, so sibling differentiation is only implicit even though the stats portion partially overlaps compare_flow_cytometry_populations.

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?

It states the conditions under which group comparisons are run ('with a sample sheet column... or by two columns'), which is real when-to guidance for two parameters. However, it never says when to choose this over the single-sample or population-comparison siblings, and it gives no prerequisites such as requiring a sample_sheet before group_by has an effect.

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