scholar-mcp

Get References

get_references

Read-only

Fetches the papers cited by a given paper, returning up to 1,000 backward references per call with pagination for larger result sets.

Instructions

Fetch papers referenced by the given paper (backward references).

Returns at most 1000 references per call; a larger limit is capped at 1000, so page further with offset.

Should the call run long it continues in the background and returns a job handle to poll with get_job_result.

Input Schema

Name	Required	Description	Default
`limit`	No	Max results (max 1000).
`fields`	No	Field set preset for returned paper records.	compact
`offset`	No	Pagination offset.
`identifier`	Yes	Paper identifier (DOI, S2 ID, ARXIV:, etc.).

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv3.1.1Nov 5, 2026
- changedInput schema / properties / limit / description
```
Previous value: -"Max results."New value: +"Max results (max 1000)."
```
Changed4 schema fields changedv1.10.0Sep 8, 2026
- 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
```
First observedv1.9.0Aug 10, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already establish readOnly/openWorld/non-destructive, but the description adds genuinely new behavior: the hard 1000-result cap, the requirement to page with offset beyond that, and the fact that long calls fall back to an async job handle polled via get_job_result. That last detail is the kind of trait an agent cannot get from the schema or annotations alone.

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?

Three short paragraphs, front-loaded with the purpose, then limits, then the async behavior. Slight redundancy: 'Returns at most 1000 references per call; a larger limit is capped at 1000' repeats the same fact and echoes the schema's '(max 1000)'.

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 values need no explanation, and the description covers the two non-obvious operational facts (cap/pagination and async job fallback). What remains unstated is how it differs from get_citation_graph for multi-hop traversal, a minor gap for a tool this simple.

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 coverage is 100%, so all four parameters are already documented, including 'Max results (max 1000)'. The description restates the cap and mentions offset paging but adds little semantic detail beyond the schema — baseline 3 applies.

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 specific verb and resource — 'Fetch papers referenced by the given paper' — and the parenthetical '(backward references)' pins the direction, which is what separates it from get_citations. It stops short of naming the sibling outright, so the agent must infer the contrast rather than being told.

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?

Usage is implied by direction: this is the backward-traversal tool versus get_citations' forward traversal. There is no explicit 'use this when...' statement and no guidance on when get_citation_graph or find_bridge_papers would be the better choice for graph-shaped questions.

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