search_genesSearch the Human Protein Atlas for human genes/proteins by gene symbol or keyword. Returns each gene with its Ensembl gene id (needed by get_protein and top_tissues), synonyms, and description. Keyless.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max genes to return (default 15). | |
| query | Yes | Gene symbol (e.g. "EGFR") or keyword (e.g. "insulin receptor"). |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "query": "EGFR"
+ },
+ {
+ "limit": 10,
+ "query": "insulin receptor"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate this is read-only, idempotent, and non-destructive. The description adds that it is 'Keyless' (no authentication needed) and lists the returned fields, providing some additional context but not significantly beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences: first states the purpose and data source, second lists key output and notes it's keyless. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple search tool with good annotations and full schema coverage, the description adequately covers the purpose, input, output, and access requirement. It could mention pagination or default limit, but the schema already handles that.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for both parameters (query, limit). The description mentions 'by gene symbol or keyword' which aligns with the query parameter description, but adds no extra meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it searches the Human Protein Atlas for human genes/proteins by gene symbol or keyword, and specifies it returns Ensembl gene id, synonyms, and description. This distinguishes it from sibling tools like get_protein and top_tissues that require the Ensembl id as input.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this tool is a prerequisite for get_protein and top_tissues by stating the returned Ensembl id is needed by those tools. However, it does not explicitly provide guidance on when to use vs. alternatives or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools have overlapping purposes: ask_pipeworx, ask_pipeworx_beta (currently identical), ask_pipeworx_grounded, deep_research, and validate_claim all handle routed research queries, while ai_visibility_check and scan_competitor_ai_presence overlap directly and the six Polymarket tools form a dense, easily confused cluster. The descriptions are detailed, but an agent will frequently struggle to pick the right tool among near-duplicate research and prediction-market options.
Names are readable and mostly snake_case, with useful prefixes like ask_pipeworx_ and polymarket_. However, conventions are mixed: some are verb_noun (search_genes, get_protein, generate_llms_txt), some are bare verbs (remember, recall, forget), and some are noun phrases (entity_profile, recent_changes, top_tissues). There is no single predictable pattern.
34 tools is above the 25+ threshold for a heavy, hard-to-navigate set, and most of them are not related to the server's stated 'Protein Atlas' identity. Only three tools actually concern proteins, while the rest form a general data-research, Polymarket, memory, and subscription toolkit that feels like several servers merged into one.
For a Protein Atlas server, the surface is severely incomplete: only search_genes, get_protein, and top_tissues cover HPA, leaving pathology, cell-line, single-cell, blood, and other major HPA dimensions unaddressed. If the intended domain is instead the broader Pipeworx data router, the protein tools are an odd vestige and the completeness story is still muddled by overlapping meta-tools.