Jean by Melad Labs

estimate_effect_size

Read-only

The effect a power calculation needs, measured from a pilot instead of guessed: two groups of one measurement in a table, standardized as Hedges' g (default), Cohen's d or Glass's Δ with its noncentral-t confidence interval (effectsize 1.0.3, reproduced), and the two-sample t design sized at the estimate and at the interval limit nearest zero. A column can be subtracted row by row first (a reference gene's Ct, giving delta-Ct). Returns the design calculate_power takes: Cohen's d for the t test, the raw difference and SD for t_raw.

Input Schema

Name	Required	Description	Default
`ci`	No	the confidence level of the interval.
`group`	No	the group compared. Left unset, the second group to appear.
`power`	No	size the design for this power; leave empty to estimate the effect only.
`table`	Yes	the pilot: a header row, then one row per observation. Tab- or comma-separated.
`value`	Yes	the column holding the measurement.
`_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.
`groups`	No	one group label per data row, in row order, separated by commas, spaces or new lines, when the table has no group column.
`paired`	No	the two groups are the same subjects measured twice, paired by row order within each group. Only applies when estimator is hedges_g or cohens_d.
`_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.
`subtract`	No	a column subtracted from the measurement row by row before anything else: a reference gene's Ct (giving delta-Ct), a baseline.
`estimator`	No	Hedges' g corrects Cohen's d's small-sample bias by the exact J(df); Cohen's d is the uncorrected standardized difference; Glass's Δ standardizes by the reference group's SD alone, for when the treatment changes the spread. Values: hedges_g (Hedges' g), cohens_d (Cohen's d), glass_delta (Glass's Δ).	hedges_g
`pooled_sd`	No	standardize by the pooled SD (Student). Off averages the two variances, with Welch's df. Only applies when estimator is hedges_g or cohens_d.
`reference`	No	the group it is compared against (the control). Left unset, the first group to appear.
`sig_level`	No	α for the sizing. Advanced.
`alternative`	No	a two-sided interval, or one bounded on one side. Values: two.sided (Two-sided), less (Less (upper bound only)), greater (Greater (lower bound only)). Advanced.	two.sided
`group_column`	No	the column naming each row's group. Or give `groups`.

Output Schema

Name	Required	Description
`design`	Yes	what calculate_power takes: the t test's d (`effect`), and the raw `difference` and `sd` for t_raw
`groups`	Yes	every group in the table: n, mean and SD of the measurement
`sizing`	Yes	pwr.t.test's sample size at the estimate and at the limit nearest zero, when power was given
`estimate`	Yes	the standardized effect
`interval`	Yes	the confidence interval: level, low, high

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 21, 2026

changedInput schema / properties / estimator / description

Previous value: -"Hedges' g corrects Cohen's d's small-sample bias by the exact J(df); Cohen's d is the uncorrected standardised difference; Glass's Δ standardises by the reference group's SD alone, for when the treatment changes the spread. Values: hedges_g (Hedges' g), cohens_d (Cohen's d), glass_delta (Glass's Δ)."New value: +"Hedges' g corrects Cohen's d's small-sample bias by the exact J(df); Cohen's d is the uncorrected standardized difference; Glass's Δ standardizes by the reference group's SD alone, for when the treatment changes the spread. Values: hedges_g (Hedges' g), cohens_d (Cohen's d), glass_delta (Glass's Δ)."

changedInput schema / properties / pooled_sd / description

Previous value: -"standardise by the pooled SD (Student). Off averages the two variances, with Welch's df. Only applies when estimator is hedges_g or cohens_d."New value: +"standardize by the pooled SD (Student). Off averages the two variances, with Welch's df. Only applies when estimator is hedges_g or cohens_d."

changedOutput schema / properties / estimate / description

Previous value: -"the standardised effect"New value: +"the standardized effect"

First observedOct 20, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds substantive behavior beyond that: the noncentral-t confidence interval, reproduction of effectsize 1.0.3, the fact that the design is sized at both the estimate and the interval limit nearest zero, and the exact shape of the returned `design`. It does not discuss failure modes or data-quality constraints, which keeps it below 5.

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 sentences, front-loaded with the purpose before the mechanics, and no filler. The sentences are long and clause-heavy with em-dash asides, which makes them denser than ideal, but each clause carries information an agent needs (estimators, CI, subtraction, return shape).

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 16-parameter tool with nested objects and an output schema, the description covers the input workflow (table, groups, subtract), the statistical behavior, and the handoff to calculate_power. Because an output schema exists it need not document return fields, and the brief return note is a bonus; the only gap is that no practical preconditions on the pilot data are stated.

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%, so the baseline is 3. The description nevertheless adds real meaning above the schema: it explains the delta-Ct use case for the subtract column ('a reference gene's Ct, giving delta-Ct'), clarifies that the result is the `design` calculate_power takes with Cohen's d for `t` and raw difference/SD for `t_raw`, and frames the estimator choice as bias-correction vs. uncorrected vs. reference-SD standardization.

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?

The description opens with a specific verb and resource ('The effect a power calculation needs, measured from a pilot instead of guessed') and immediately names the three estimator variants it computes. It also positions itself in the pipeline against the sibling calculate_power by naming the `design` object it returns, so an agent can distinguish it from the power-sizing siblings without opening the 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?

It gives clear context for when this tool is the right one: when an effect size must be measured from pilot data rather than guessed, and it names calculate_power as the downstream consumer. It stops short of an explicit exclusion or a named alternative to use in a different situation, so it is a strong 4 rather than a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Jean by Melad Labs 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?