Skip to main content
Glama
Sign In
preprint-fulltext

preprint-fulltext

by genecell
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

get_fulltext

Retrieve structured full-text sections from a preprint DOI or URL, defaulting to the latest version or a specified one. Use it to extract readable preprint content for analysis.

Instructions

Retrieve structured full-text sections for a preprint DOI (or URL). Resolves to the latest version by default; pass version for a specific one.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "doi": "<doi>"
    },
    "name": "get_fulltext"
  }
}

Input Schema

NameRequiredDescriptionDefault
doiYes
mathNo
linksNo
sourceNo
scriptsNo
versionNo
citationsNo
allow_htmlNo
subscriptsNo
as_markdownNo
fetch_tablesNo
paragraph_sepNo
legends_as_sectionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv0.2.1
    • addedInput schema / properties / allow_html
      Added value: +{
+  "type": "boolean"
+}
    • addedInput schema / properties / citations
      Added value: +{
+  "enum": [
+    "drop",
+    "keep"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / fetch_tables
      Added value: +{
+  "type": "boolean"
+}
    • addedInput schema / properties / legends_as_section
      Added value: +{
+  "type": "boolean"
+}
    • addedInput schema / properties / links
      Added value: +{
+  "enum": [
+    "inline",
+    "text"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / math
      Added value: +{
+  "enum": [
+    "text",
+    "tex",
+    "placeholder"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / paragraph_sep
      Added value: +{
+  "type": "string"
+}
    • addedInput schema / properties / scripts
      Added value: +{
+  "enum": [
+    "caret",
+    "unicode"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / source
      Added value: +{
+  "enum": [
+    "europepmc",
+    "s3",
+    "html",
+    "arxiv"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / subscripts
      Added value: +{
+  "enum": [
+    "flat",
+    "underscore"
+  ],
+  "type": "string"
+}
  2. First observedv0.1.0

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations, the description carries the full burden. It discloses only the default-version behavior; it says nothing about whether the call performs a network fetch, what happens when the DOI resolves to no full text, rate limits, or what formats/sources are chosen by default among the six enum parameters.

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?

Two sentences, front-loaded with the action and target, and zero wasted wording. The brevity is a virtue structurally even though the same brevity creates coverage gaps scored elsewhere.

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

Completeness2/5

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

A 13-parameter, no-annotation, no-output-schema tool needs considerably more explanation than two sentences. The description does not tell the agent what the returned 'sections' look like or how the many formatting options affect output, so correct invocation is largely guesswork.

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

Parameters2/5

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

Schema description coverage is 0% across 13 parameters, and the description explains only `version`. The twelve other parameters (math, links, source, scripts, citations, allow_html, subscripts, as_markdown, fetch_tables, paragraph_sep, legends_as_section) get no meaning from either the schema or the description, so the agent cannot know what they change in the output. It also says 'or URL' while the schema requires a `doi` string.

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?

States a clear verb and resource ('Retrieve structured full-text sections for a preprint DOI') and implicitly separates itself from get_metadata by asking for full text rather than metadata. It does not name siblings, but the resource is specific enough that an agent can distinguish it.

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

Usage Guidelines3/5

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

'Resolves to the latest version by default; pass version for a specific one' gives a real usage rule for versioning. But there is no guidance on when to use this instead of get_metadata or resolve, and no mention of fallbacks or prerequisites.

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