Search 200M+ scientific papers. Use 'topic' for predefined compliance searches (dora, mica, aml, etc.) or 'query' for free text.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | relevance,citationCount,year | |
| limit | No | Max 20 | |
| query | No | Free text search | |
| topic | No | Predefined: dora,mica,aml,amlr,stablecoin,operational_resilience,ai_governance,agent_security,defi_regulation,cbdc,tokenization,regtech,suptech,esma,eba,psd2,eidas,gdpr,basel | |
| year_to | No | ||
| year_from | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the two search modes (topic and query), which is helpful. But it does not mention return format, pagination, or any limitations beyond the schema, leaving the agent with some uncertainty about the exact behavior.
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 single, well-structured sentence that leads with the core purpose and then includes actionable usage guidance. Every part earns its place with no redundancy.
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?
With no output schema and no annotations, the description could be more complete about what the response looks like or how results are ordered. It covers the main topic/query distinction but omits information about year filtering and output structure, which is a notable gap for a 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?
The description adds meaningful context for 'topic' and 'query' by explaining their intended use, going beyond the schema's descriptions. It doesn't cover the undocumented year_from/year_to parameters, but those are reasonably inferable from their names, and the parameter coverage is moderate.
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's function with a specific verb and resource ('Search 200M+ scientific papers'). It distinguishes itself from siblings by mentioning both predefined compliance searches (topic) and free text (query), making its scope evident and differentiating it from tools like arxiv_search.
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 gives explicit guidance on when to use 'topic' vs 'query' parameters, which is a clear usage direction. However, it does not compare with sibling tools or state exclusions, so it falls short of the highest score.
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 target distinct resources (papers, authors, citations, DOIs). arxiv_search and search_papers both search for papers, but they are differentiated by corpus (preprints vs all). compliance_research is a convenience wrapper for compliance topics but is still distinct.
Tool names mix noun-noun (author_papers, citation_graph), noun-verb (arxiv_search, doi_lookup), and verb-noun (search_papers) patterns. While each name is readable, there is no consistent verb_noun convention, making it harder to predict tool names.
At 11 tools, the set is well-scoped for a research discovery platform. Each tool covers a necessary aspect: search, metadata, authors, citations, recommendations, trending, and system health.
The surface covers core research workflows: searching, retrieving details, author exploration, citation analysis, recommendations, and trending. Minor gaps exist (e.g., no journal-specific search or batch export), but agents can accomplish typical tasks without dead ends.