Search academic papers from PubMed.
Args:
query: Search query string (e.g., 'machine learning').
max_results: Maximum number of papers to return (default: 10).
Returns:
List of paper metadata in dictionary format.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| max_results | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description is the main source of behavioral disclosure. It states that the tool returns a list of paper metadata dictionaries and that max_results caps the number of returned papers, but it does not mention pagination, rate limits, authentication, or exact result fields.
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 a compact docstring with clear Args and Returns sections, no filler, and information is front-loaded.
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 two-parameter search tool, the description covers arguments and return type. It could be improved by specifying the exact dictionary keys or any result limits, but it is sufficient for basic invocation.
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 0%, but the description fully documents both parameters: query with an example and max_results with its default and meaning as a maximum count. This compensates for the missing schema descriptions.
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 uses the specific verb 'search' with an explicit resource 'PubMed' and summarizes the result as academic paper metadata. This clearly distinguishes it from siblings like search_arxiv or search_medrxiv.
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?
It clearly identifies PubMed as the target database, implying use when searching PubMed literature. However, it does not explicitly discuss 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.
Multiple tools appear to serve the same purpose, such as search_arxiv and search-arxiv, or papers-search-basic, paper-search-advanced, search_papers, and search. The download/read tools for different sources follow similar patterns, but some return 'not supported' messages, making it unclear which tools are actually functional.
Tool names mix snake_case, kebab-case, and bare verbs without a consistent pattern. For example, about_nanci, analysis-citation-network, download-full-paper-arxiv, fetch, and search_arxiv all coexist, and the same action for different sources alternates conventions (search-arxiv vs search_arxiv).
With 53 tools, the server is heavily over-scoped. Many tools are redundant or near-duplicates, such as six source-specific search tools plus an aggregate search, and the inclusion of both paper and clinical trial tools in one server creates unnecessary bloat.
The server covers a wide range of research workflows, including search, download, read, citations, authors, and clinical trials. However, several tools (crossref/pubmed download/read) are non-functional dead ends, and the redundancy makes it harder to navigate the surface.