Skip to main content
Glama

legume_qtl

Read-onlyIdempotent

QTL and GWAS results for legumes: soybean (SoyBase QTL on genetic maps plus GWAS; marker positions on Wm82.a2 = Ensembl glycine_max), common bean (G19833 v1 = Ensembl phaseolus_vulgaris; some GWAS on G19833 v2), cowpea (IT97K-499-35 v1) and peanut (Tifrunner v2) from LIS; faba bean QTL markers from 56 studies (Faba Bean Genome Consortium compilation, positions on Hedin/2 v2 and projected to the Ensembl Hedin/2 v1 assembly); lentil protein and amino acid GWAS on the diversity panel (KnowPulse, CDC Redberry v2 = LIS lentil genes); chickpea, lentil, pea, faba bean, lupin, grass pea and pigeonpea QTL and GWAS from pulsedb.org (Cool Season Food Legume Database). Search by trait words (e.g. 'seed oil', 'pod dehiscence', 'chocolate spot', 'lysine'; soybean traits use SoyBase names such as 'SCN', 'SDS', 'Sclero', so check legume_qtl_traits) and/or a physical region (species + chromosome as in the marker assembly or the Ensembl name, start, end). Returns each QTL (genetic map, linkage group, cM interval, markers) or marker-trait association (marker, p-value where reported) with study, DOI and marker positions; ensembl_region gives genes_in_region arguments where the markers are on the Ensembl assembly (faba bean: positions projected from Hedin/2 v2 to v1 through gene matches, approximate), lis_region gives legume_genes_in_region arguments (lentil).

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": "legume_qtl"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNo
limitNo
startNo
traitNo
speciesNo
chromosomeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive, open-world, so the description's job is context — and it delivers: multi-source aggregation, per-species assembly/version pinning (Wm82.a2, G19833 v1/v2, Hedin/2 v1 vs v2), the caveat that faba bean positions are projected and approximate, and 'p-value where reported' for incomplete data. It does not mention result counts, pagination, or default limit behavior, which is the remaining gap for a search tool.

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 content earns its length, but the structure does not: it is effectively two enormous run-on sentences where the data-source inventory precedes the actual instruction, so an agent must parse ~100 words before learning that this is a trait/region search. Assembly-version detail is essential; the ordering is not.

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 six-parameter, multi-source tool with no output schema, the description covers return shape (QTL with genetic map, linkage group, cM interval, markers; MTA with marker and p-value; study and DOI) plus the machine-usable ensembl_region and lis_region handoff fields. Missing pieces are paging/limit semantics and whether filters combine as AND or OR.

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?

With 0% schema description coverage the description must carry all six parameters, and it largely does: trait (with example values and a pointer to legume_qtl_traits for naming conventions), species, chromosome (with the assembly-vs-Ensembl naming ambiguity called out), start and end as a physical region. Only 'limit' (default 30) is left completely unexplained.

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 concrete resource (QTL and GWAS results) and enumerates the exact per-species sources and assemblies covered, and it explicitly differentiates itself from the sibling legume_qtl_traits ('soybean traits use SoyBase names ... so check legume_qtl_traits'). It loses a point because the operative verb ('Search by trait words ... and/or a physical region') is buried in the second half rather than front-loaded, so the first read is a data catalog rather than a statement of what the tool does.

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 concrete query modes (trait words vs. species+chromosome+start/end) with worked trait examples, and it routes the agent to legume_qtl_traits for SoyBase trait names and forward to genes_in_region / legume_genes_in_region via the ensembl_region and lis_region outputs. It never states exclusions or when not to use it, and it does not say whether trait and region filters can be combined.

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