hn-tech-signal-mcp

Overview Schema Source Related Servers Discussions Admin

arxiv_search

Read-onlyIdempotent

Search arXiv for papers matching your query, optionally restrict to an AI/ML category, and get results sorted by submission date.

Instructions

Search arXiv for papers matching a query, sorted by submission date.

Searches title, abstract and author fields. Optionally restrict to a specific AI/ML category.

Args: params (ArxivSearchInput): - query (str): Search terms (e.g. 'LLM agents tool use') - category (Optional[str]): arXiv category filter - limit (int): Papers to return (1–20)

Returns: str: JSON with query, category, count, papers[]. Each paper: id, title, abstract, authors, published, url, pdf.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`params`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`count`	Yes
`query`	Yes
`papers`	Yes
`category`	Yes
`fetched_at`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedv0.5.0Sep 30, 2026

addedOutput schema / $defs

Added value: +{
+  "ArxivPaper": {
+    "additionalProperties": false,
+    "properties": {
+      "abstract": {
+        "description": "First 400 characters",
+        "title": "Abstract",
+        "type": "string"
+      },
+      "authors": {
+        "description": "First five",
+        "items": {
+          "type": "string"
+        },
+        "title": "Authors",
+        "type": "array"
+      },
+      "categories": {
+        "description": "All categories, primary included",
+        "items": {
+          "type": "string"
+        },
+        "title": "Categories",
+        "type": "array"
+      },
+      "category": {
+        "description": "Primary category",
+        "title": "Category",
+        "type": "string"
+      },
+      "id": {
+        "title": "Id",
+        "type": "string"
+      },
+      "pdf": {
+        "title": "Pdf",
+        "type": "string"
+      },
+      "published": {
+        "title": "Published",
+        "type": "string"
+      },
+      "title": {
+        "title": "Title",
+        "type": "string"
+      },
+      "url": {
+        "title": "Url",
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "title",
+      "abstract",
+      "authors",
+      "published",
+      "category",
+      "categories",
+      "url",
+      "pdf"
+    ],
+    "title": "ArxivPaper",
+    "type": "object"
+  }
+}

addedOutput schema / additionalProperties
```
Added value: +false
```

addedOutput schema / properties / category

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "title": "Category"
+}

addedOutput schema / properties / count

Added value: +{
+  "title": "Count",
+  "type": "integer"
+}

addedOutput schema / properties / fetched_at

Added value: +{
+  "title": "Fetched At",
+  "type": "string"
+}

addedOutput schema / properties / papers

Added value: +{
+  "items": {
+    "$ref": "#/$defs/ArxivPaper"
+  },
+  "title": "Papers",
+  "type": "array"
+}

addedOutput schema / properties / query

Added value: +{
+  "title": "Query",
+  "type": "string"
+}

removedOutput schema / properties / result

Removed value: -{
-  "title": "Result",
-  "type": "string"
-}

changedOutput schema / required

Previous value: -[
-  "result"
-]New value: +[
+  "query",
+  "category",
+  "fetched_at",
+  "count",
+  "papers"
+]

changedOutput schema / title

Previous value: -"arxiv_searchOutput"New value: +"ArxivSearchOutput"

First observedv0.2.4Jul 11, 2026

TDQS

A3.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: it searches title, abstract, and author fields, sorts by submission date, and returns a structured JSON payload. It does not mention rate limits or auth, but those are minor omissions given the annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, then systematically lists Args and Returns. It is appropriately sized for a search tool, though the explicit Returns section is somewhat redundant because an output schema exists.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple search tool with annotations covering safety and an output schema present, the description is largely complete: it covers field scope, sorting, category filtering, and return shape. The main gap is guidance against the sibling arxiv_latest, which would help avoid misselection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Given the reported 0% schema description coverage, the description compensates by enumerating query, category, and limit, including examples for query and category and the 1–20 range for limit. It does not explain category syntax beyond the example, but it adds enough meaning for correct invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: search arXiv for papers matching a query, with sorting by submission date and field coverage. It is clear enough to distinguish from generic search tools, but it does not explicitly contrast with the sibling arxiv_latest, which is the closest alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description only explains that category filtering is optional and does not say when to use this tool instead of arxiv_latest or other search siblings. Usage context is implied by the purpose but not guided, so it falls short of explicit when-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server