Skip to main content
Glama

legume_gene

Read-onlyIdempotent

Chickpea or lentil gene from the Legume Information System (these genomes are not in Ensembl Plants), or a gene of the extra faba bean and lentil gene sets: location, functional description, LIS legume gene family, curated lentil symbols and gene lists (flowering, pigment, resistance gene analogues), best protein match to the reference gene set, and link. gene: a gene ID (e.g. 'Ca1g000100', 'Lcu.2RBY.1g000010', 'Vfaba.Hedin2.R2.1g000001'), a curated lentil symbol (e.g. 'LcFIE'), an Ensembl faba bean v1 ID (lists its v2/Tiffany counterparts) or words from the description (e.g. 'flowering locus T'). Datasets: 'chickpea' = Cicer arietinum CDC Frontier (kabuli) assembly v3 (gene IDs like Ca1g000100, chromosomes chr1-chr8); 'chickpea_kabuli_v1' = the original kabuli CDC Frontier genes (Ca_00001 IDs used in most chickpea papers) placed on the UWA kabuli v2.6.3 assembly (Ca1-Ca8); 'chickpea_desi' = desi ICC 4958 genes (also Ca_ IDs, but different genes from the kabuli Ca_ IDs) on the UWA desi v3.0 assembly (Ca1-Ca8); 'lentil' = Lens culinaris CDC Redberry assembly v2 (IDs like Lcu.2RBY.1g000010, chromosomes Chr1-Chr7); extra gene sets (no LIS families; best protein match given): 'faba_v2' = faba bean Hedin/2 v2 (Vfaba.Hedin2.R2.1g000001, chr1_partA/B, chr2-chr6; matched to Ensembl Hedin/2 v1), 'faba_tiffany' = faba bean Tiffany (Vfaba.Tiffany.R1..., matched to Ensembl v1), 'lentil_greenstar' = lentil CDC Greenstar (Lcu.1GRN.1g000010) and 'lentil_ervoides' = Lens ervoides IG 72815 (Ler.1DRT.1g000010), both matched to LIS CDC Redberry v2. Gene families (LIS legume.fam3) also cover pea (Cameor, Psat... = Ensembl Plants pisum_sativum IDs), soybean (Wm82.a2, Glyma.01G000600 = Ensembl GLYMA_01G000600) and Medicago truncatula (A17 v5, MtrunA17Chr...).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "gene": "<gene>"
    },
    "name": "legume_gene"
  }
}

Input Schema

NameRequiredDescriptionDefault
geneYes
limitNo
datasetNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, so the bar is lower, and the description still adds real context: which datasets carry LIS families versus only best-protein matches, and how extra gene sets are matched to references. It omits any mention of the limit/pagination behavior or result shaping for keyword searches, which would matter when a query matches many genes.

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 purpose and accepted gene inputs are front-loaded, which is good, but the body is a dense run-on block mashing datasets, assemblies, chromosome naming and gene families into long semicolon chains. Nearly every clause carries information, yet the lack of structure (bullets or line breaks between datasets) makes it harder to scan than its length alone would justify.

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?

With no output schema, the description correctly spends effort describing what fields come back and which datasets lack LIS families. It is nearly complete for a three-parameter lookup, with the only real gap being the undocumented limit/pagination behavior and no explicit routing advice against sibling tools.

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 0%, so the description must carry parameter meaning and it largely does: 'gene' is defined with concrete ID formats, curated symbols and free-text keyword usage, and 'dataset' is exhaustively enumerated with assembly, ID-pattern and chromosome details per value. The 'limit' parameter (default 20) is never mentioned, leaving one of three parameters undocumented.

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 the resource (a chickpea/lentil/faba gene record from the Legume Information System) and enumerates exactly what is returned: location, functional description, LIS gene family, curated lentil symbols, best protein match and link. It partially differentiates from siblings by stating these genomes are not in Ensembl Plants, which hints at why legume_gene exists alongside find_gene, but no sibling is named explicitly.

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?

Guidance is implicit: the dataset enumeration tells an agent which collection to pick, and the gene examples show accepted input forms. However, there is no explicit 'use this when... and use legume_family / legume_genes_in_region / find_gene instead when...' routing, so the agent must infer alternatives from the sibling list.

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