Skip to main content
Glama
Sign In
Scholar MCP

Scholar MCP

by Liyux3
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Read a paper's main text or a page range

read_paper
Read-onlyIdempotent

Read a paper's text by page range, inspect selected figures and tables, and jump to appendix sections.

Instructions

Read a paper's text, inspect figures and tables, or jump to its appendix.

Returns page-aware Markdown from pages 1-10 by default, with selectors for figures and tables. Native structured articles are used when a PDF is unavailable, with original section IDs and continuation locators. Use visual to inspect a selected item. The temporary PDF is cleaned up; use download_paper to keep a local copy.

Input Schema

NameRequiredDescriptionDefault
pagesNoOne-indexed page range. The default usually reaches the conclusion of an AI conference paper. Use ranges such as "11-20" for appendices. At most 20 pages can be read per call. For structured articles, use the returned next_pages or xml:ID selector; these are not PDF pages.1-10
visualNoOptional selector returned by this tool, such as "Figure 3", "Table 2", or "page 5". Returns one focused visual with its text.
paper_idYesPaper identifier (S2 ID, DOI, ArXiv:ID, etc.)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.9.0
    • changedInput schema / properties / pages / description
      Previous value: -"One-indexed page range. The default usually reaches the conclusion\nof an AI conference paper. Use ranges such as \"11-20\" for appendices.\nAt most 20 pages can be read per call."New value: +"One-indexed page range. The default usually reaches the conclusion\nof an AI conference paper. Use ranges such as \"11-20\" for appendices.\nAt most 20 pages can be read per call. For structured articles, use\nthe returned next_pages or xml:ID selector; these are not PDF pages."
  2. Changed9 schema fields changedv0.8.3
    • removedInput schema / properties / extract_text
      Removed value: -{
-  "default": true,
-  "description": "If True, extract and return text. If False, just download PDF.",
-  "type": "boolean"
-}
    • removedInput schema / properties / max_pages
      Removed value: -{
-  "default": 0,
-  "description": "Maximum pages to extract (0 = all pages)",
-  "type": "integer"
-}
    • addedInput schema / properties / pages
      Added value: +{
+  "default": "1-10",
+  "description": "One-indexed page range. The default usually reaches the conclusion\nof an AI conference paper. Use ranges such as \"11-20\" for appendices.\nAt most 20 pages can be read per call.",
+  "type": "string"
+}
    • removedInput schema / properties / save_dir
      Removed value: -{
-  "default": "",
-  "description": "Directory to save PDF (default: configured download directory)",
-  "type": "string"
-}
    • addedInput schema / properties / visual
      Added value: +{
+  "default": "",
+  "description": "Optional selector returned by this tool, such as \"Figure 3\",\n\"Table 2\", or \"page 5\". Returns one focused visual with its text.",
+  "type": "string"
+}
    • addedOutput schema / additionalProperties
      Added value: +true
    • removedOutput schema / properties
      Removed value: -{
-  "result": {
-    "type": "string"
-  }
-}
    • removedOutput schema / required
      Removed value: -[
-  "result"
-]
    • removedOutput schema / x-fastmcp-wrap-result
      Removed value: -true
  3. First observedv0.6.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive behavior, yet the description still adds meaningful traits: page-aware Markdown output, fallback to native structured articles when no PDF exists, continuation locators, and cleanup of the temporary PDF. The only minor gap is no mention of failure modes for invalid paper_id.

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 the purpose, then layered details on defaults, fallbacks, and cleanup. The standalone line 'Use visual to inspect a selected item' slightly interrupts flow but is a useful pointer rather than waste.

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

Completeness5/5

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

With an output schema present, the description need not explain return shapes, and it covers the remaining behavioral essentials: default range, page-range limits referenced in schema, PDF-vs-structured fallback, and cleanup semantics. An agent has everything needed to call it correctly.

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

Parameters3/5

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

Schema description coverage is 100%, fully documenting pages, visual, and paper_id, so the baseline applies. The description reinforces the figure/table selector concept and the 'visual' parameter's role, but adds no syntax or constraints beyond what the schema states.

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?

Opens with a specific verb and resource ('Read a paper's text') and enumerates the distinct modes: body text, figure/table inspection, and appendix jumps. This clearly separates it from siblings like search_papers (discovery) and download_paper (persistence).

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?

Gives concrete usage context: default pages 1-10 usually reach a conclusion, ranges like '11-20' reach appendices, and it routes to 'visual' for focused inspection and to download_paper for keeping a copy. It doesn't explicitly contrast with paper_info or search_papers, but the reading-vs-discovery boundary is clear enough.

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