Skip to main content
Glama

gene_in_assemblies

Read-onlyIdempotent

Corresponding genes of a Brassica gene in other genome assemblies: 32 Brassica assemblies distributed by BnaOmics: B. napus Darmor-bzh v10, Express 617, NY7, the eight HZAU genomes (Gangan, Zheyou 73, Shengli, Tapidor, Quinta, Westar, No2127; ZS11 is the BnIR genome) and the HZAU pan-genome reference, ZS11, Westar and Laurentian ONT assemblies, ZS4-2, ZS9, HTR001, Zhongyou 821 and ZS11 (FAFU); B. carinata zd-1; B. juncea AU213 and tumida v2; B. nigra YZ12151, Ni100 v2, C2; B. oleracea HDEM, JZS v2, Korso, OX-heart; B. rapa Chiifu v3.0 and v2.5, Z1 v2 (assembly ids like Bnapus_Darmor_v10, Bnapus_Westar_ONT, Brapa_Chiifu_v3; B. napus genes are matched to Ensembl Darmor v4.1, B. rapa to Chiifu, B. oleracea to TO1000, B. juncea and B. nigra to Ensembl B. juncea, B. carinata to B. juncea + B. oleracea). gene: an Ensembl Plants gene ID or name ('BnaC09g12820D', 'GSBRNA2T00000001001', 'Bra000001', 'Bo1g001000') or a gene ID of one of these assemblies (returns its Ensembl match, then the other assemblies). Matches are DIAMOND best protein hits to the Ensembl gene (identity, query coverage, and whether the pair is a reciprocal best hit); each gene has its location and a genome browser link. assembly restricts to one assembly id; reciprocal_only keeps reciprocal best hits.

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": "gene_in_assemblies"
  }
}

Input Schema

NameRequiredDescriptionDefault
geneYes
assemblyNo
reciprocal_onlyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.3/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, open-world, so the safety profile is covered. Beyond that, the description discloses the matching methodology (DIAMOND best protein hits with identity, query coverage, and reciprocal-best-hit status), the resolution step (an assembly-local gene ID is first matched to its Ensembl gene), and the ordering of results (Ensembl match first, then other assemblies). That is meaningful behavioral context not present in structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense run-on paragraph, dominated by an exhaustive enumeration of 32 assemblies with cultivar variants and matching-reference notes. That list has some value as enum-like reference data, but it is unstructured prose that buries the actionable parameter guidance in the middle of the block. The critical sentences about 'gene', 'assembly', and 'reciprocal_only' should be front-loaded and separated.

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 3-parameter tool with no output schema, the description does explain the returned fields (identity, query coverage, reciprocal-best-hit flag, location, genome browser link) and the result ordering, which is enough to call it confidently. What is missing is any positioning against closely related siblings and any statement about empty results or match-confidence interpretation.

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 largely meets it. It explains accepted 'gene' formats with concrete examples ('BnaC09g12820D', 'GSBRNA2T00000001001', 'Bra000001', 'Bo1g001000') and the fallback behavior for assembly-specific IDs, defines 'assembly' as restricting to one assembly id and supplies assembly id formats (Bnapus_Darmor_v10, Brapa_Chiifu_v3), and defines 'reciprocal_only' as keeping only reciprocal best hits.

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 clause states the specific operation: given a Brassica gene, return its corresponding genes in other genome assemblies. It enumerates the target assemblies and the matching basis (DIAMOND best protein hits), so an agent knows exactly what resource is being searched. It does not, however, distinguish itself from the sibling 'orthologues' or 'blast_sequence' tools.

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 explicit when-to-use or when-not-to-use statement, and no alternative sibling is named (orthologues, pangenome_gene, blast_sequence all plausibly overlap). Usage is only inferable from the phrase 'corresponding genes of a Brassica gene in other genome assemblies'. The guidance on the 'assembly' and 'reciprocal_only' flags is parameter-level, not selection-level.

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