Search PubMed biomedical literature database (NIH). Returns articles with titles, authors, journals, and links.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Search query (e.g. "COVID-19 vaccines", "CRISPR gene editing") | |
| sort | No | Sort order: relevance or date | relevance |
| limit | No | Number of results (max 20, default 10) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It implies read-only behavior but does not explicitly state that it only searches metadata, mentions no rate limits, authentication requirements, or pagination details. The return format is described but behavioral constraints are absent.
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 concise (two sentences) and front-loaded with the core purpose. Every sentence adds value without extraneous detail.
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?
Although there is no output schema, the description lists the key fields returned (titles, authors, journals, links), which is sufficient for basic understanding. The three parameters are all covered. Missing are nuances like date ranges or advanced query syntax, but overall it is fairly complete for a straightforward search tool.
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 description coverage is 100%, so the parameters are already well-documented. The description adds minimal value beyond the schema, except for examples for the 'q' parameter. Baseline 3 is appropriate.
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 action 'Search PubMed biomedical literature database (NIH)' and specifies the return content ('articles with titles, authors, journals, and links'). It distinguishes itself from sibling tools like get_citations and search_arxiv by naming the database and return format.
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 guidance is provided on when to use this tool versus alternatives (get_citations, search_arxiv). The description does not mention contexts where PubMed is preferred or when another tool would be more appropriate.
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.
Each tool targets a distinct database or function (citations, arXiv, PubMed). However, get_citations can also search by topic, which might overlap with search_arxiv or search_pubmed in intent, though results differ.
All tool names follow a consistent verb_noun pattern with lowercase and underscores: get_citations, search_arxiv, search_pubmed.
Three tools is a minimal but reasonable set for an academic search server. It covers major repositories and citation lookup, but leaves room for more specialized searches.
The server covers arXiv, PubMed, and Crossref citations, but lacks other major databases (e.g., Google Scholar, IEEE Xplore) and full-text retrieval, which are notable gaps for a comprehensive academic search tool.