Scholar Feed

by io.github.YGao2005

Fetch Full Text

fetch_fulltext

Read-only

Read arXiv papers' actual text, by section. Section selection controls context cost: ask for the one or two you need, not whole papers — 'all' is ~13.5KB a paper, 8 of them ~108KB. Section labels are inferred: check low_confidence_sections before calling one the paper's own. Sourced from arXiv's section-tagged HTML, then LaTeX, then PDF; a 404 means all three failed.

Input Schema

TableJSON Schema

Name	Required	Description
`arxiv_id`	No	arXiv ID of one paper.
`sections`	No	One section name or an array. Defaults to 'all' for one paper; no default for a batch.
`arxiv_ids`	No	Up to 8 arXiv IDs, one entry per paper. `sections` is required past one ID.

Output Schema

TableJSON Schema

Name	Required	Description
`note`	No
`source`	No
`results`	No	Batch mode: one entry per paper, in request order. A failed paper is an entry with ok:false and an `error` code, never a failed call.
`arxiv_id`	No
`sections`	No	Per-section text; null means the paper has no such section.
`full_text`	No	Backup text, PDF fallback only.
`table_captions`	No
`missing_sections`	No	Requested sections the paper lacks.
`requested_section`	No
`available_sections`	No	Which sections this paper has; 'no such section' is not 'extraction failed'.
`requested_sections`	No
`section_provenance`	No	How each section was labelled: abstract_block, heading, heading_loose, subsection, latex_heading, pdf_heading, or positional. Absent, with low_confidence_sections, when labelling is unknown; that is not verification.
`low_confidence_sections`	No	Sections labelled positionally: a guess (~50% accurate, hand-audited) at what sits between the introduction and the results, and on surveys or theory papers often not a method at all. Verify against the text before citing it as the paper's method. Present whenever section_provenance is; [] means nothing looks uncertain.
`requested_section_available`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed20 schema fields changedSep 29, 2026

changedInput schema / properties / arxiv_id / description

Previous value: -"arXiv ID of the paper"New value: +"arXiv ID of one paper."

addedInput schema / properties / arxiv_ids

Added value: +{
+  "description": "Up to 8 arXiv IDs, one entry per paper. `sections` is required past one ID.",
+  "items": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 8,
+  "minItems": 1,
+  "type": "array"
+}

addedInput schema / properties / sections / anyOf

Added value: +[
+  {
+    "enum": [
+      "all",
+      "abstract",
+      "introduction",
+      "related_work",
+      "method",
+      "results",
+      "conclusion"
+    ],
+    "type": "string"
+  },
+  {
+    "items": {
+      "enum": [
+        "all",
+        "abstract",
+        "introduction",
+        "related_work",
+        "method",
+        "results",
+        "conclusion"
+      ],
+      "type": "string"
+    },
+    "type": "array"
+  }
+]

changedInput schema / properties / sections / description

Previous value: -"'results' (default): lean ~800-char results/experiments excerpt + table captions. 'all': full paper (abstract, intro, method, results, conclusion, related work) — much larger payload."New value: +"One section name or an array. Defaults to 'all' for one paper; no default for a batch."

removedInput schema / properties / sections / enum
```
Removed value: -[
-  "results",
-  "all"
-]
```
removedInput schema / properties / sections / type
```
Removed value: -"string"
```
removedInput schema / required
```
Removed value: -[
-  "arxiv_id"
-]
```

addedOutput schema / properties / available_sections

Added value: +{
+  "description": "Which sections this paper has; 'no such section' is not 'extraction failed'.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / full_text

Added value: +{
+  "description": "Backup text, PDF fallback only.",
+  "type": "string"
+}

addedOutput schema / properties / low_confidence_sections

Added value: +{
+  "description": "Sections labelled positionally: a guess (~50% accurate, hand-audited) at what sits between the introduction and the results, and on surveys or theory papers often not a method at all. Verify against the text before citing it as the paper's method. Present whenever section_provenance is; [] means nothing looks uncertain.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / missing_sections

Added value: +{
+  "description": "Requested sections the paper lacks.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / note
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / requested_section
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / requested_section_available
```
Added value: +{
+  "type": "boolean"
+}
```

addedOutput schema / properties / requested_sections

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / results

Added value: +{
+  "description": "Batch mode: one entry per paper, in request order. A failed paper is an entry with ok:false and an `error` code, never a failed call.",
+  "items": {
+    "additionalProperties": {},
+    "properties": {
+      "arxiv_id": {
+        "type": "string"
+      },
+      "error": {
+        "description": "invalid_id | not_extractable | extraction_failed | timeout",
+        "type": "string"
+      },
+      "ok": {
+        "type": "boolean"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

removedOutput schema / properties / results_text

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "description": "Results/experiments excerpt (default 'results' mode)."
-}

addedOutput schema / properties / section_provenance

Added value: +{
+  "additionalProperties": {
+    "type": "string"
+  },
+  "description": "How each section was labelled: abstract_block, heading, heading_loose, subsection, latex_heading, pdf_heading, or positional. Absent, with low_confidence_sections, when labelling is unknown; that is not verification.",
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}

changedOutput schema / properties / sections / description

Previous value: -"Per-section text (sections='all')."New value: +"Per-section text; null means the paper has no such section."

removedOutput schema / properties / source / description

Removed value: -"Where the text came from (e.g. arxiv)."

First observedSep 6, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only cover read-only safety, and the description adds substantial behavior: context-cost magnitudes per section and per batch, that section labels are inferred (with low_confidence_sections to verify), the source fallback chain HTML → LaTeX → PDF, and that a 404 means all three failed.

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?

Front-loaded with the core action, then dense but load-bearing detail on cost, label reliability, and sourcing. No sentence is filler.

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 covering returns and annotations covering safety, the description fills the remaining gaps an agent needs: cost budgeting, label-confidence caveats, source fallback, and failure semantics.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema: the context cost of 'all', the batch-of-8 scale, and the need to consult low_confidence_sections for inferred labels.

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?

States a specific verb (Read) and resource (arXiv papers' actual text) with the scoping mechanism (by section). It is clearly distinguishable from metadata-oriented siblings like get_paper or search_papers.

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 clear operational guidance: 'ask for the one or two you need, not whole papers' with concrete cost figures for 'all'. It does not, however, explicitly name when to prefer this over get_paper or other siblings.

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

All Scholar Feed tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.