Skip to main content
Glama

find_germplasm

Read-onlyIdempotent

Find Brassica genebank accessions by accession number or name: Brassica, Camelina, Sinapis and Raphanus accessions from GBIF, with the holding genebank (FAO WIEWS code) and accession number; mostly Svalbard Global Seed Vault safety duplicates. Passport data are minimal (no traits); request seed from the holding genebank. Also INRAE GnpIS Brassica collections via FAIDARE (B. napus, B. oleracea and B. rapa) with taxon, holding institute, country of origin, status, pedigree and panels.

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": {
      "name": "<name>"
    },
    "name": "find_germplasm"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
limitNo

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 declare read-only, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: the upstream sources queried, that records are mostly Svalbard safety duplicates, and that passport data are minimal so seed must be obtained from the holding genebank. It stops short of describing result ordering or pagination behavior.

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 key capability and lookup key are front-loaded in the first clause, and the following sentences add source and limitation detail rather than filler. Slightly dense and line-wrapped, but every sentence carries information.

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 usefully describes what comes back (holding genebank with FAO WIEWS code, accession number, taxon, institute, country, status, pedigree, panels). The main gap is lack of any statement about the limit parameter or result volume, which matters for a two-parameter search tool.

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?

With 0% schema description coverage, the description must carry the burden; it does clarify that the required 'name' parameter accepts either an accession number or a name, which the bare schema does not. It says nothing about 'limit' (default 10) or result-count behavior, leaving half the parameters undocumented.

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?

Opens with a specific verb+resource ('Find Brassica genebank accessions by accession number or name') and then enumerates the exact genera and data sources (GBIF, FAIDARE/INRAE GnpIS) it covers. An agent can clearly distinguish this germplasm-lookup tool from gene, expression, or SNP 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 Guidelines3/5

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

The description implies its scope (passport-level accession lookup, not trait data) and warns 'no traits; request seed from the holding genebank,' which implicitly routes phenotype/trait queries elsewhere. However, it names no alternative tool and gives no explicit when-to-use/when-not-to-use rule against siblings such as brapi_germplasm_studies or pangenome_accessions.

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