references"What does paper [DOI] cite" / "references in [paper]" / "what sources does this paper use" — DOIs cited BY the given DOI (the paper's reference list / bibliography). Use for citation-graph traversal, literature review, source tracking.
| Name | Required | Description | Default |
|---|---|---|---|
| doi | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| references | No | DOIs cited by the given DOI |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "doi": "10.1371/journal.pone.0123456"
+ },
+ {
+ "doi": "10.1038/nature12345"
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "references": {
+ "description": "DOIs cited by the given DOI",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds meaningful semantic context by clarifying that the tool returns the paper's reference list, which is not implied by the tool name alone. It does not contradict annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loads the phrasing with common user queries, and efficiently communicates the core function and use cases without any wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With one simple parameter, comprehensive annotations, and an existing output schema, the description fully covers the necessary context. It explains what the tool does and when to use it, leaving no significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The only parameter 'doi' is not described in the schema (0% coverage), but the description effectively conveys that 'DOI' refers to the paper whose references are to be retrieved, through phrases like 'given DOI' and the query examples. This is adequate for a single parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that this tool returns the references/bibliography (DOIs cited BY the given DOI), using explicit query examples like 'What does paper [DOI] cite'. It distinguishes itself from sibling tools by specifying the direction of the citation relationship, which is critical for citation-graph traversal.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear usage context: 'Use for citation-graph traversal, literature review, source tracking.' However, it does not explicitly state when NOT to use it or name alternatives (e.g., the sibling 'citations' for finding papers that cite a given DOI).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Multiple tools have unclear boundaries: ask_pipeworx and ask_pipeworx_beta are described as currently identical, and citation vs citations differ only by pluralization while actually accepting different ID types (OCI vs DOI). The server is named Opencitations but 31 of 37 tools serve unrelated purposes, so an agent cannot infer what the set is for without reading very long descriptions.
All names are snake_case and family prefixes (polymarket_*, ask_pipeworx_*, pipeworx_*) give some predictability. However, conventions are mixed: bare resource nouns (citation, citations, references, metadata) coexist with verb_noun tools (resolve_entity, validate_claim) and noun phrases (recent_changes, entity_profile, deep_research), so there is no single pattern that lets an agent predict tool names.
37 tools is well past the 25+ threshold for a heavy set, and most are redundant with the server's own router tools — ask_pipeworx already reaches 5,759 underlying tools, making many direct tools overlapping conveniences. The scope also wildly overshoots the server name: only 6 of 37 tools serve the Opencitations citation-graph domain.
For the named OpenCitations domain, the core citation-graph read operations exist (metadata, incoming citations, outgoing references, counts, OCI record lookup), but there is no paper/DOI discovery or search tool — an agent must already possess a DOI, a dead end for title/author queries. The broader accidental domain (data routing, company research, prediction markets, monitoring) is covered unusually well, but that does not serve the server's stated purpose.