Skip to main content
Glama

wheat_mutants

Read-onlyIdempotent

Induced mutations and natural variants in and around a bread wheat gene. source 'ems' (default): EMS mutant lines of tetraploid Kronos and hexaploid Cadenza with exome-capture sequencing (Krasileva et al. 2017; 2,735 lines), giving the line ID to order, e.g. Cadenza1158; 'diversity': exome-capture variants of 890 landraces and cultivars (He et al. 2019) and 103 Watkins landraces; 'all'. Every variant Ensembl assigns to the gene is kept: coding, splice, UTR, intron and upstream/downstream (within 5 kb). consequence filters: 'truncating' (stop gained, splice donor/acceptor, start/stop lost), 'missense', 'coding', 'splice', 'utr', 'intron', 'flanking' (upstream/downstream), 'regulatory' (flanking + UTR) or a Sequence Ontology term. homoeologues=True adds the A/B/D copies (to stack knockouts). gene: symbol or any IWGSC ID (converted to RefSeq v1.1); positions are RefSeq v1.0.

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": "wheat_mutants"
  }
}

Input Schema

NameRequiredDescriptionDefault
geneYes
limitNo
sourceNoems
consequenceNo
homoeologuesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: Ensembl-based variant assignment rules (coding, splice, UTR, intron, flanking), the 5 kb flank boundary, and the critical coordinate caveat that gene IDs are converted to RefSeq v1.1 while positions remain v1.0. It omits any mention of the default limit=100 truncation, which matters for result interpretation.

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?

The scope statement is front-loaded and the rest is dense, factual parameter guidance with little filler; citations and line counts are arguably padding but support provenance judgment. The semicolon-chained style and unquoted lists make it slightly harder to scan than it needs to be.

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?

For a five-parameter, no-output-schema tool this is close to adequate: sources, filters, coordinate versions and the 'line ID to order' hint are all present. What is absent is any sense of the returned record shape (fields per variant, ordering, how truncation behaves), which the agent must guess at since no output schema exists.

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 carries the full burden, and it does so for four of five parameters: gene (symbol or any IWGSC ID, converted to RefSeq v1.1), source (ems default / diversity / all, with dataset provenance), consequence (enumerated values plus Sequence Ontology terms), and homoeologues (adds A/B/D copies). The limit parameter is never mentioned, leaving result-size control undocumented in both schema and description.

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 opening sentence gives a specific resource and scope: induced mutations and natural variants within and around a named bread wheat gene, with the ±5 kb window and the datasets involved spelled out. An agent can immediately tell this is a gene-centric mutant/variant retrieval tool, though it never names a sibling (e.g. wheat_variants_in_region, wheat_mutant_line) to draw the boundary explicitly.

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?

Strong in-parameter guidance: it explains what 'ems' vs 'diversity' vs 'all' select, lists the accepted consequence categories, and notes that homoeologues=True is for stacking knockouts. What is missing is routing guidance — when to prefer this over the region-based or line-based sibling tools — so the agent must infer the choice from scope alone.

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