Jean — Molecular Biology & Genomics

plan_rnaseq_experiment

Read-only

How many biological replicates an RNA-seq experiment needs when the question is about the WHOLE experiment rather than one gene: the exact negative-binomial test with the per-gene α derived from a target false discovery rate across m genes of which m1 are expected to move (RnaSeqSampleSize 2.23.0, Zhao et al. 2018; the test is Robinson & Smyth 2008's, edgeR's exactTest), or the AVERAGE power across genes whose effects differ, with the FDR controlled (ssizeRNA 1.3.3, Bi & Liu 2016).

Input Schema

Name	Required	Description	Default
`m`	No	genes tested. Only applies when method is exact.
`n`	No	biological replicates in the control group, when solving power. Only applies when solve_for is power.
`m1`	No	genes expected to be differentially expressed. Only applies when method is exact.
`fdr`	No	the false discovery rate to control across the experiment.
`pi0`	No	the proportion of genes with no effect. A list asks the question once per proportion, which is how the answer's sensitivity to it is read. Only applies when method is average_power.
`count`	No	λ₀, the average read count for a prognostic gene in the control group. Only applies when method is exact.
`max_n`	No	the largest replicate count to search. Only applies when method is average_power. Advanced.
`power`	No	the power to reach, when solving n.
`sigma`	No	the common within-gene standard deviation on that scale. Only applies when method is average_power.
`_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.
`counts`	No	a pilot's average read count per gene. With `dispersions`, the power is computed for each of these genes and averaged, instead of for one idealised gene. Only applies when method is exact.
`method`	No	which question. `exact` powers one prognostic gene with the exact negative-binomial test at an α derived from the FDR; `average_power` asks what the mean power across genes is when each gene's effect is drawn from a normal. Values: exact (Exact negative-binomial test), average_power (Average power across genes).	exact
`_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.
`effect_sd`	No	the spread of those true effects ACROSS genes; 0 would make every gene identical. Only applies when method is average_power.
`solve_for`	No	size the experiment, or score a design you already have. Values: n (Replicates per group), power (Power).	n
`dispersion`	No	φ₀, the negative-binomial dispersion of a prognostic gene — the square of the biological coefficient of variation. Only applies when method is exact.
`size_ratio`	No	k, the ratio of treatment to control group size. Only applies when method is exact. Advanced.
`dispersions`	No	the dispersion of each gene in `counts`, in the same order. Only applies when method is exact.
`effect_mean`	No	the mean of the normal each gene's true log-fold-change is drawn from. Only applies when method is average_power.
`fold_change`	No	ρ, the minimum fold change to detect in a prognostic gene. Only applies when method is exact.
`normalization_ratio`	No	w, the ratio of the two groups' normalization factors. Only applies when method is exact. Advanced.

Output Schema

Name	Required	Description
`n`	Yes	replicates per group (the control group, when the groups differ)
`rows`	Yes	each (n, power) the search evaluated, one row per n in n order, or every (pi0, n, power) for average power
`alpha`	Yes	the per-gene α the FDR target implies
`curve`	Yes	power against replicates, which is the plot this question is read from
`power`	Yes	the power that number of replicates gives
`rCall`	Yes	the R call that reproduces the answer
`method`	Yes	which of the two questions was answered
`solved`	Yes	which quantity was solved
`perGene`	Yes	the power of each gene in `counts`, when a pilot distribution was given

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 21, 2026

removedInput schema / properties / normalisation_ratio

Removed value: -{
-  "default": 1,
-  "description": "w, the ratio of the two groups' normalisation factors. Only applies when method is exact. Advanced.",
-  "minimum": 0,
-  "type": "number"
-}

addedInput schema / properties / normalization_ratio

Added value: +{
+  "default": 1,
+  "description": "w, the ratio of the two groups' normalization factors. Only applies when method is exact. Advanced.",
+  "minimum": 0,
+  "type": "number"
+}

First observedOct 20, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=false, destructiveHint=false, so the safety profile is covered. The description adds real value beyond that by naming the underlying methods, their packages/versions (RnaSeqSampleSize 2.23.0, ssizeRNA 1.3.3) and citations, which signals exactly what computation will be run. It stops short of any behavioral caveats such as convergence limits or search bounds.

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 core question is front-loaded correctly, but the two sentences are long and heavily parenthetical, packing version numbers, author-year citations and package names into the same breath as the substantive explanation. The provenance is defensible for a method-selection tool, yet it crowds out clearer guidance on when to prefer this over sibling tools.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 21 parameters, nested objects and an output schema present, the description reasonably need not explain return values. What it lacks is the disambiguation an agent needs among the many adjacent power/simulation siblings, which is the main completeness gap for a tool of this complexity.

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 description coverage is 100% and the per-parameter text already carries the method-applicability constraints, so the baseline is 3. The description complements this by framing the two modes the parameters divide into, letting an agent map parameters to the correct method branch before opening the schema.

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: 'How many biological replicates an RNA-seq experiment needs', then splits the answer into two well-defined statistical framings (exact negative-binomial test vs average power across genes). It does not, however, distinguish itself from the several power-related siblings (calculate_rnaseq_power, simulate_rnaseq_power, calculate_power, estimate_effect_size).

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 two-sentence description implicitly tells the reader which of the two internal methods answers which question, and the schema reinforces that with 'Only applies when method is exact/average_power'. But there is no explicit when-to-use/when-not guidance relative to the sibling power tools, which is the more likely ambiguity for an agent.

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?