Skip to main content
Glama

expression_genes

Read-onlyIdempotent

Genes characteristic of a tissue/stage or responsive to a treatment in one Expression Atlas experiment. Baseline experiment + group (text matched to group labels, e.g. 'root', 'grain'): genes with TPM >= min_tpm in a matching group ranked by specificity = (max TPM in matching groups + 1) / (max TPM in other groups + 1). Differential experiment + contrast (text matched to contrast names or IDs): significant genes, direction 'up' or 'down', ranked by |log2FC|. Use expression_experiments() for group and contrast names.

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": {
      "experiment": "<experiment>"
    },
    "name": "expression_genes"
  }
}

Input Schema

NameRequiredDescriptionDefault
groupNo
limitNo
min_tpmNo
contrastNo
directionNoup
experimentYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

The annotations already declare this as a read-only, idempotent, non-destructive, open-world operation, so the safety profile is covered. The description adds genuine behavioral detail beyond that: text-based matching to group labels or contrast names/IDs, a TPM threshold filter (min_tpm), and the exact specificity and |log2FC| ranking formulas that determine result order.

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 description is dense but front-loaded: the purpose statement leads, then the baseline mode with its ranking formula, then the differential mode, then a pointer to the sibling tool. It justifies its length by covering two modes, though the formulas make some sentences heavy.

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?

With six parameters, no schema descriptions, and no output schema, the definition covers the core query semantics and ranking well but omits the default/max behavior of limit and any hint about the experiment identifier format, so an agent still has gaps when constructing a call.

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?

Schema description coverage is 0%, so the description must carry the parameter burden. It explains group (text matched to group labels, with examples 'root', 'grain'), contrast (matched to contrast names or IDs), min_tpm (TPM >= threshold), and direction ('up' or 'down'), but says nothing about limit or the format/identifier of the required experiment parameter, leaving two of six 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?

The description uses a specific verb and resource ('genes characteristic of a tissue/stage or responsive to a treatment in one Expression Atlas experiment') and then splits the tool into two distinct modes, baseline and differential, so an agent can tell exactly what it returns in each case.

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?

It clearly states which inputs select which mode (group for baseline, contrast for differential) and directs the agent to expression_experiments() to obtain valid group and contrast names. It gives no explicit exclusion against other expression siblings such as gene_expression, but the mode-selection guidance is concrete and actionable.

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