search_pubmedSearch PubMed for biomedical literature. Returns title, authors, journal, year, DOI, abstract, and PMID for each result.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | PubMed search query | |
| max_results | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently states that it returns a list with specific fields (title, authors, journal, etc.), which communicates the output structure. However, it does not disclose potential limitations like result ordering, pagination, or error behavior, which are relevant for a search tool.
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 exceptionally concise, using two clearly separated sentences to state purpose and return fields. All content is essential, with zero redundancy or filler.
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 no output schema and no annotations, the description provides the essential context: what it searches and what it returns. Its brevity is acceptable given the tool's simplicity, but it lacks any guidance on when to favor it over closely related sibling tools, which would improve completeness in the broader tool context.
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?
The description adds no parameter-specific meaning beyond the schema. It does not mention how to formulate a query or that max_results controls the result limit. With 50% schema description coverage (query is described, max_results is not), the description fails to compensate for the missing parameter semantics, leaving the agent to infer the purpose of max_results from its schema attributes alone.
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 the resource 'PubMed' and clearly states the domain 'biomedical literature.' It enumerates the exact return fields (title, authors, journal, year, DOI, abstract, PMID), which unambiguously distinguishes it from sibling tools like query_chembl or query_clinicaltrials.
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 implicitly suggests when to use the tool—when you need PubMed literature search results—by naming PubMed and biomedical literature. However, it does not explicitly contrast with alternatives or state exclusions, such as 'for clinical trials use query_clinicaltrials.' The guidance is implied through purpose rather than clearly articulated.
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 responsibilities: search, search_claims, search_preprint_flags, and claidex_claim_risk_matrix all query claim/failure data, while rank_documents_by_embedding and rerank_documents both perform relevance ranking. The compatibility-oriented fetch/search tools add further confusion because their names collide with fetch_research_url and search_claims.
Names are grouped by prefixes (claidex_, query_, search_, run_) but the groups use different conventions, and bare verbs like 'fetch' and 'search' sit alongside prefixed forms like 'fetch_research_url' and 'search_claims'. The pattern is readable but not uniform.
24 tools is at the heavy end for an MCP server; while the breadth reflects many biomedical data sources and utilities, the count includes several meta/compatibility tools that could be consolidated. It is borderline but not unreasonable.
The surface covers the core biomedical workflows: searching claims, retrieving full claim content, querying failure graphs, checking preprints, and looking up drugs/trials/targets/adverse events. Minor gaps exist, such as no direct way to fetch a single clinical trial by ID beyond the search function, and no write/update operations for claims, but these are likely outside the read-only research scope.