get_referencePomBase: look up a curated S. pombe publication by its PubMed id (e.g. "PMID:11739790") and return its title, citation, authors, year, abstract, and how many genes it annotates. Keyless.
| Name | Required | Description | Default |
|---|---|---|---|
| pmid | Yes | A PubMed id, with or without the "PMID:" prefix, e.g. "PMID:11739790" or "11739790". |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "pmid": "PMID:11739790"
+ },
+ {
+ "pmid": "12345678"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, idempotentHint, etc. The description adds key behavioral details: returns specific fields and is keyless (no API key needed), which goes 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?
One concise sentence front-loaded with 'PomBase', listing specific return fields and example PubMed ID. No wasted 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 1-parameter read-only tool with annotations, the description adequately covers purpose and return values. Missing error handling details but acceptable.
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 already describes the pmid parameter format. The description adds minor examples but does not provide significant additional meaning.
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 looks up a curated S. pombe publication by PubMed ID and returns specific fields (title, citation, authors, etc.). It distinguishes itself from siblings by being specific to PomBase and S. pombe.
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?
No explicit guidance on when to use vs alternatives. The description implies it is for PomBase/S. pombe references, but lacks when-not-to-use or alternative tool references.
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 heavily overlapping purposes, notably ask_pipeworx vs ask_pipeworx_beta vs ask_pipeworx_grounded, and the cluster of polymarket tools covers adjacent prediction-market analysis territory. The PomBase-specific tools are distinct, but the overall set creates real selection ambiguity.
Most names follow a readable snake_case style and many use verb-first patterns, but there is notable mixing: ask_pipeworx is a brand-style exception, entity_profile and polymarket_arbitrage are noun-first, and remember/recall/forget form an inconsistent trio. Not chaotic, but not a clean predictable convention.
33 tools is excessive for a server named Pombase, where only get_gene and get_reference actually serve that domain. Even as a broad data-research server, the count is above the 25-tool threshold and includes many auxiliary utilities that feel bolted on rather than part of a focused surface.
The PomBase-specific coverage is severely thin: only systematic-ID gene lookup and PubMed-ID reference lookup, with no gene-name search, annotations browsing, phenotype data, or sequence access. The broader Pipeworx surface is extensive, but for the apparent Pombase purpose, agents will frequently hit dead ends.