Skip to main content
Glama

Metis · Librarian — Search Semantic Scholar

search_semantic_scholar

Search Semantic Scholar by topic to discover papers via citation graph and insert matches into research briefs for citation-aware literature review.

Instructions

Search Semantic Scholar for papers on a topic (citation-graph discovery).

Complements PubMed (scan_pubmed_alerts) and OpenAlex (scan_openalex) with
Semantic Scholar's 200M+ paper graph and citation counts. Free public Graph
API, no key required. Matched papers are inserted into news_briefs with
source_type='article' (domain 'Semantic Scholar') so the Librarian and the
dashboard surface them like any other discovered paper.

Args:
    query: Free-text topic to search (e.g. "malaria elimination surveillance").
           Defaults to your configured PubMed/topic query if empty.
    max_results: Maximum papers to retrieve (default 10, max 100).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_semantic_scholar"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNo
max_resultsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.2

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does substantial work: it discloses the access model ('Free public Graph API, no key required') and, critically, a write side effect — matched papers are inserted into news_briefs with a specific source_type and domain. It omits rate limits, failure behavior, and whether re-runs dedupe, which keeps it from a 5.

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?

Front-loaded with purpose and differentiator, then a compact Args block — well structured and easy to scan. The 'Librarian and dashboard surface them' clause is slightly padded but still conveys where results land.

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?

An output schema exists, so return-value detail is rightly omitted. Combined with the side-effect disclosure, key/API requirements, and both parameter defaults, an agent has nearly everything needed; the remaining gap is the absence of any guidance about result volume or duplicate handling across repeated runs.

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?

Schema coverage is 0%, so the description must compensate, and it does: query gets an example and a documented fallback behavior ('Defaults to your configured PubMed/topic query if empty'), and max_results gets both a default and a hard ceiling (max 100) that the schema does not express. Only the exact string-format expectations for query remain unstated.

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

Purpose5/5

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

The description opens with a specific verb+resource ('Search Semantic Scholar for papers on a topic') and immediately scopes it as citation-graph discovery. It explicitly positions itself against named siblings (scan_pubmed_alerts, scan_openalex) and the surrounding corpus (search_literature, search_pdf_knowledge), so an agent can distinguish it without opening a schema.

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

Usage Guidelines4/5

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

It names the competing sources and states the differentiator ('200M+ paper graph and citation counts'), which gives an agent a real selection rationale. It stops short of explicit when-not-to-use guidance relative to other literature search tools in this very large sibling set, so it falls short of a 5.

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

Deploy Server

Other Tools