scholar-mcp

Get Citations

get_citations

Read-only

Fetch papers that cite a given paper, with filters for publication year, field of study, and minimum citation count. Supports pagination and background jobs for deep paging.

Instructions

Fetch papers that cite the given paper (forward citations).

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

Paging deeply to satisfy min_citations can run long; such a call 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 (pagination, max 1000).
`fields`	No	Field set preset for returned paper records.	compact
`offset`	No	Pagination offset.
`year_end`	No	Filter citing papers published up to this year.
`identifier`	Yes	Paper identifier (DOI, S2 ID, ARXIV:, etc.).
`year_start`	No	Filter citing papers published from this year.
`min_citations`	No	Minimum citation count of citing papers. Applied client-side (S2 does not support this filter on the citations endpoint). Papers with unknown citation counts are excluded. Pagination (``offset``/``limit``) is applied to the filtered results. The tool paginates through up to 10 000 upstream results to find qualifying papers.
`fields_of_study`	No	Filter by field of study.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv3.1.1Nov 5, 2026

changedInput schema / properties / limit / description

Previous value: -"Max results (pagination)."New value: +"Max results (pagination, max 1000)."

changedInput schema / properties / min_citations / description

Previous value: -"Minimum citation count of citing papers.\nApplied client-side (S2 does not support this filter on\nthe citations endpoint).  Papers with unknown citation\ncounts are excluded.  Pagination (``offset``/``limit``)\nis applied to the filtered results.  The tool paginates\nthrough up to 10 000 upstream results to find qualifying\npapers."New value: +"Minimum citation count of citing papers.\nApplied client-side (S2 does not support this filter on\nthe citations endpoint). Papers with unknown citation\ncounts are excluded. Pagination (``offset``/``limit``)\nis applied to the filtered results. The tool paginates\nthrough up to 10 000 upstream results to find qualifying\npapers."

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

A4.7/5.0

Behavior5/5

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

Adds real behavior beyond the readOnly/openWorld annotations: a hard 1000-result cap that silently truncates larger limit values, the escape hatch via offset, and the fact that deep min_citations paging escalates into a background job returning a handle for get_job_result. These are non-obvious async and truncation semantics an agent could not infer from annotations or schema.

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?

Three short paragraphs, front-loaded with what the tool does, then limits, then the async escape hatch. Every sentence carries actionable information; no restatement of the title or name.

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?

For an 8-parameter paginated read tool with an output schema, the description covers the two things an agent must know to call it correctly: truncation/capping behavior and the background-job escalation path. Return value shape is handled by the output schema, so nothing material is missing.

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 the schema does not: that limit is capped at 1000 (schema says 'max 1000' but not that oversized values are silently clamped) and that offset is the paging mechanism for that cap and for filtered results. Other parameters (year_start, year_end, fields_of_study) are left entirely to the schema, which already documents them well.

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 and resource ('Fetch papers that cite the given paper') and immediately disambiguates direction with '(forward citations)', which cleanly separates it from the sibling get_references (backward citations). No ambiguity about what is returned.

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 operational guidance: page with offset past the 1000 cap, and poll get_job_result when a min_citations call continues in the background. It does not explicitly say when to prefer get_citation_graph or generate_citations instead, so the alternative-selection guidance is implicit rather than complete.

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