Jean by Melad Labs

discover_gene_tree_discordance

Read-only

Find the genes whose own alignment rejects the species tree. Each named alignment file is one gene, its records the taxa, named as the species tree's tips.

Input Schema

Name	Required	Description	Default
`seed`	No	seed for the bootstrap. Each gene draws from seed + its own index, so a gene's p does not depend on the rest of the corpus. Advanced.
`alpha`	No	false discovery rate at which a gene counts as rejecting the species tree.
`_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.
`sh_form`	No	how each replicate is measured: from its best tree, as Shimodaira and Hasegawa (1999) and Goldman et al. (2000) define the test, or from its worst, as phangorn's SH.test computes it. They agree when the replicates are symmetric. Values: published (Published (from the best tree)), phangorn (phangorn (from the worst tree)). Advanced.	published
`_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.
`alignments`	Yes	the gene alignments: library file names, each an aligned multi-FASTA with one record per taxon, the record names being the species tree's tips.
`correction`	No	Benjamini–Hochberg (independent or positively dependent tests) or Benjamini–Yekutieli (any dependence; less power). Values: BH (Benjamini–Hochberg), BY (Benjamini–Yekutieli).	BH
`replicates`	No	RELL bootstrap replicates of the SH test. The smallest nonzero p is 1 / replicates; a p of 0 means no replicate reached the observed difference, which evidence reads as 1 / (replicates + 1).
`species_tree`	Yes	the species tree in Newick, tips named as the alignments' records. Rooted or not; it is tested unrooted.
`gamma_categories`	No	discrete Gamma rate categories; 1 fits no rate variation among sites. Advanced.

Output Schema

Name	Required	Description
`genes`	Yes	every gene: sites, each candidate tree's log-likelihood and SH p, the species tree's p and q
`sweep`	Yes	the full result
`rejected`	Yes	genes whose alignment rejects the species tree at the chosen false discovery rate
`discordant`	Yes	genes whose best tree is not the species tree, rejected or not
`alternatives`	Yes	each alternative tree some gene prefers, with how many prefer it and how many of those reject the species tree

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 21, 2026

changedInput schema / properties / replicates / description

Previous value: -"RELL bootstrap replicates of the SH test. The smallest p it can give is 1 / replicates."New value: +"RELL bootstrap replicates of the SH test. The smallest nonzero p is 1 / replicates; a p of 0 means no replicate reached the observed difference, which evidence reads as 1 / (replicates + 1)."

First observedOct 20, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare this a safe, closed-world read operation, so the safety profile is covered. The description adds the data-model constraint that alignment files must map one-to-one onto genes and share tip names with the species tree, but says nothing about the underlying test (SH test, bootstrap, FDR) — that behavior lives only in the parameter descriptions.

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 tight sentences with the purpose front-loaded and zero filler. The second sentence packs several facts but stays readable; nothing is wasted.

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 10 parameters (8 advanced), a nested _subject object, and an output schema, the description covers only the two required inputs and omits the statistical framing (alpha, correction, replicates, seed independence) that determines what 'rejects' actually means. Adequate but with a clear gap on both methodology and sibling routing.

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 coverage is 100%, so the schema already documents seed, alpha, correction, replicates, sh_form, and gamma_categories in detail. The description reinforces the meaning of `alignments` and `species_tree` (tips must match) but adds little the schema does not already say; baseline 3 is appropriate.

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 and outcome: 'Find the genes whose own alignment rejects the species tree'. The second sentence clarifies the unit of analysis (one alignment file = one gene). However, it never distinguishes itself from the very similar sibling discover_tree_incongruence, leaving the agent to guess which tool answers 'is my gene tree discordant'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use/when-not guidance and no named alternative, despite at least two plausible siblings (discover_tree_incongruence, alignment_agreement). The input-format sentence describes shape, not usage conditions, so the agent must infer applicability entirely from the name.

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?