Skip to main content
Glama

sch_get

Retrieve scholarly research articles using DOI, arXiv ID, or URL to access academic papers and metadata for research purposes.

Instructions

Alias of sch.get

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
doiNo
arxivIdNo
urlNo

Implementation Reference

  • Core handler function schGet that fetches scholarly article metadata from Crossref (DOI), arXiv (ID), or extracts DOI from URL.
    export async function schGet(args: { doi?: string, arxivId?: string, url?: string }) {
      if (args.doi) {
        const url = `https://api.crossref.org/works/${encodeURIComponent(args.doi)}`;
        const res = await fetchWithLimits(url, 8000, 1024*1024);
        if (res.body) {
          const it = JSON.parse(res.body.toString('utf-8')).message;
          return {
            title: (it.title && it.title[0]) || '',
            authors: (it.author || []).map((a:any) => [a.given, a.family].filter(Boolean).join(' ')),
            year: (it.created?.['date-parts']?.[0]?.[0]) || '',
            doi: it.DOI || '',
            url: it.URL || '',
            abstract: (it.abstract || '').replace(/<[^>]+>/g, ''),
            source: 'crossref'
          };
        }
      }
      if (args.arxivId) {
        const items = await arxivSearch(`id:${args.arxivId}`, 1);
        return items[0] || null;
      }
      if (args.url) {
        const m = args.url.match(/10\.\d{4,9}\/[-._;()/:A-Z0-9]+/i);
        if (m) return schGet({ doi: m[0] });
      }
      return null;
    }
  • src/server.ts:184-189 (registration)
    Registration of the 'sch_get' tool in the MCP server, which proxies to the schGet handler.
    server.tool('sch_get', 'Alias of sch.get',
      schGetShape, OPEN,
      async ({ doi, arxivId, url }) => {
        const res = await schGet({ doi, arxivId, url });
        return { content: [{ type: 'text', text: JSON.stringify(res) }] };
      }
  • Zod schema defining the input parameters for the sch_get tool.
    const schGetShape = { doi: z.string().optional(), arxivId: z.string().optional(), url: z.string().optional() };
  • src/server.ts:177-183 (registration)
    Primary registration of the 'sch.get' tool (sch_get is an alias), proxying to schGet handler.
    server.tool('sch.get', 'Get scholarly metadata by DOI/arXivId/URL.',
      schGetShape, OPEN,
      async ({ doi, arxivId, url }) => {
        const res = await schGet({ doi, arxivId, url });
        return { content: [{ type: 'text', text: JSON.stringify(res) }] };
      }
    );
Behavior3/5

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

The description adds minimal behavioral context beyond the openWorldHint annotation. It indicates this is an alias, which suggests identical functionality to sch.get, but doesn't confirm this or explain why the alias exists. No additional behavioral traits like rate limits, authentication needs, or specific constraints are mentioned. The annotation isn't contradicted.

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

Conciseness5/5

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

The description is maximally concise - a single three-word phrase. There's no wasted space or unnecessary elaboration. However, this extreme conciseness comes at the cost of meaningful information content.

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

Completeness1/5

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

For a tool with 3 parameters (0% schema coverage), no output schema, and only one annotation (openWorldHint), the description is completely inadequate. It doesn't explain what the tool does, what the parameters mean, what it returns, or when to use it versus the original sch.get. The agent would be left guessing about fundamental aspects of the tool.

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

Parameters1/5

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

With 0% schema description coverage and 3 parameters (doi, arxivId, url), the description provides absolutely no information about what these parameters mean or how they should be used. The description doesn't mention parameters at all, leaving the agent with no semantic understanding beyond the parameter names themselves.

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

Purpose2/5

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

The description 'Alias of sch.get' is tautological - it restates the tool name without explaining what the tool actually does. While it indicates this is an alias for another tool (sch.get), it doesn't state what that tool does, leaving the purpose unclear. The agent would need to examine sch.get to understand the functionality.

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 provides no guidance on when to use this tool versus alternatives. It doesn't explain why this alias exists when sch.get is already available, nor does it indicate any differences in behavior or appropriate contexts for use. The sibling tools list shows sch.get exists, but no comparison is provided.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/khanhs-234/tool4lm'

If you have feedback or need assistance with the MCP directory API, please join our Discord server