Skip to main content
Glama

gene_expression

Read-onlyIdempotent

Where and when a Brassica gene is expressed, and under which treatments it changes, from Expression Atlas, SRA study SRP159041 (B. napus leaf cold, heat and drought; quantified by askBrassica) and 69 B. napus SRA projects from BrassicaEDB (abiotic and biotic stress, chemical treatments, development, genotypes; experiment IDs PRJNA...). gene: Ensembl gene ID (e.g. GSBRNA2T00000001001 for B. napus, Bra000001 for B. rapa) or a gene name find_gene resolves. Baseline: TPM (median over replicates, with range) for the top_groups highest-expressed tissues/stages per experiment. Differential: every contrast where the gene is significant (adjusted p < 0.05, |log2FC| >= 1). experiment restricts to one accession; otherwise the max_experiments baseline experiments with the highest TPM are detailed and the rest listed with their maximum.

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_expression"
  }
}

Input Schema

NameRequiredDescriptionDefault
geneYes
experimentNo
top_groupsNo
max_experimentsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / max_experiments
      Added value: +{
      +  "default": 20,
      +  "title": "Max Experiments",
      +  "type": "integer"
      +}
  2. First observed

TDQS

A4.3/5.0
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; the description adds substantial behavior beyond that: significance cutoffs (adjusted p < 0.05, |log2FC| >= 1) for differential results, TPM median-over-replicates baseline with range, and truncation behavior where only the top TPM experiments are detailed and the remainder are listed with their maximum. It does not discuss result size, empty-result cases, or latency, keeping it short of a 5.

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?

It is front-loaded correctly (purpose, then sources, then parameter behavior), but the body is a run-on with unbalanced parentheses and embedded provenance strings (SRP159041, PRJNA..., experiment counts) that consume space without helping invocation. The information density is high, yet the lack of line breaks or labeled sections makes the parameter explanations hard to scan.

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 four-parameter tool with no output schema, the description does the heavy lifting: it names the data sources, states the statistical thresholds, and describes what is returned for both baseline and differential sections, including what changes when results are truncated. Remaining gaps are secondary, such as the exact response structure and behavior when a gene has no expression records.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden, and it does: 'gene' gets format examples for both B. napus and B. rapa plus the find_gene resolution path; 'experiment' gets its accession semantics and its effect on the rest of the behavior; 'top_groups' is defined as highest-expressed tissues/stages per experiment; 'max_experiments' is defined as the number of highest-TPM baseline experiments detailed. Every one of the four parameters gains meaning not present in the schema.

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-and-resource statement: 'Where and when a Brassica gene is expressed, and under which treatments it changes,' naming the organism, the data sources (Expression Atlas SRP159041 and 69 BrassicaEDB SRA projects), and the quantification pipeline. An agent can immediately tell this is a per-gene expression lookup rather than a gene search (find_gene) or a pangenome/annotation tool.

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?

Gives concrete context for use: pass an Ensembl gene ID or a name that find_gene resolves, and optionally restrict to one experiment via 'experiment'. It also explains the default fallback behavior when no experiment is given. It stops short of naming an explicit alternative (e.g. bnir_expression) or stating when not to use this tool.

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