get_geneResolve a gene to its Entrez gene id and canonical info via cBioPortal. Accepts a HUGO symbol (e.g. "TP53", "BRCA1") or an Entrez gene id. Returns entrez_gene_id, symbol, and type.
| Name | Required | Description | Default |
|---|---|---|---|
| gene | Yes | HUGO gene symbol (e.g. "TP53") or Entrez gene id. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds value by specifying the external datasource (cBioPortal) and the exact returned fields. This goes beyond annotations without contradiction, giving the agent useful context about API backend and response structure.
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?
The description is two sentences, directly stating the action, input format, and output fields. Every word is informative with no redundancy. It is front-loaded with the action and source, making it easy to scan.
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 tool with one parameter and no output schema, the description fully covers what the tool does, what it accepts, and what it returns. No gaps remain given the tool's complexity and the presence of comprehensive annotations.
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% and the schema description for 'gene' already states 'HUGO gene symbol (e.g. "TP53") or Entrez gene id.' The description repeats this identical information, adding no additional meaning beyond what the schema provides. Baseline 3 is appropriate for full coverage with no extra semantics.
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 the tool resolves a gene to its Entrez gene id and canonical info via cBioPortal. It specifies accepted inputs (HUGO symbol or Entrez gene id) and expected outputs (entrez_gene_id, symbol, type). This is specific and distinguishes the tool from siblings, as no other sibling appears to perform gene resolution.
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 when to use the tool (when you need to resolve a gene identifier) but does not provide explicit when-not-to-use or alternative tools. Given the simplicity and specificity, the usage context is clear but could be improved with exclusions or references to other tools.
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.
Most tools have clearly distinct purposes, but ask_pipeworx_beta is an intentional near-duplicate of ask_pipeworx, and several polymarket/entity tools overlap in scope. The descriptions do enough to disambiguate most pairs, but the duplicate beta routing tool introduces real ambiguity.
All names use snake_case, but the pattern varies: verb_noun (get_gene, search_studies), noun_noun (polymarket_edges, pipeworx_trending), and product-prefixed verbs (ask_pipeworx, bet_research). There is no single consistent convention, though the names remain readable.
35 tools is a heavy surface, and the vast majority (31) are unrelated to cBioPortal; only four tools actually belong to the named domain. This makes the count inappropriate for a cancer-genomics MCP server, as the set is bloated with out-of-scope utilities.
For a cBioPortal server, only metadata-level tools exist (gene lookup, study details, cancer types, study search); core cBioPortal data access — mutations, copy-number alterations, clinical data, molecular profiles, sample-level queries — is entirely missing. The tool surface severely under-covers the named domain.