Search arXiv for academic papers using a query. Filter results by publication year range or restrict to tech/computer science topics.
Search arxiv only.
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Max results. | |
| query | Yes | Search query. | |
| year_to | No | Latest publication year. | |
| tech_only | No | Restrict to tech/computer-science. | |
| year_from | No | Earliest publication year. |
Changes observed during successful MCP inspections.
v2.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure, but it only says 'Search arxiv only.' It does not mention return format, pagination, ordering, or any side effects. Search is inherently read-only, yet the description adds no behavior context beyond the bare action.
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 efficient sentence with zero filler, making it concise. However, it borders on under-specification—it provides no contextual front-loading about behavior or scope beyond the tool name, so while it is concise, it sacrifices substance.
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?
Given five parameters, no output schema, and a long list of sibling search tools, an agent needs more context about what the results look like, how 'arxiv only' differs from search_all or other source-specific tools, and how parameters like year_from/year_to shape the search. The one-line description leaves all of this unstated.
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 input schema fully documents all five parameters, including defaults and descriptions. The tool description adds no additional semantic detail about parameters, matching the baseline for fully documented schemas.
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?
'Search arxiv only.' states a clear verb (Search) and resource (arxiv), and the word 'only' signals scope that distinguishes it from broader or other-source search tools. It doesn't specify what kind of results are returned (papers, metadata, full text), but the core purpose is unambiguous.
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 word 'only' implies this tool is for arxiv-specific search and not for other indexes, but it never names alternatives like search_all or search_scopus or states explicit when-to-use/when-not-to-use conditions. Guidance is implied rather than explicit, so an agent must infer the boundary from sibling names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.