Retrieves the papers a given paper references (backward citations) using its bibcode, DOI, arXiv ID, or SciX ID; specify rows to limit results.
Get papers referenced by a given paper (backward citations). Accepts a bibcode, DOI, arXiv ID, or SciX ID.
| Name | Required | Description | Default |
|---|---|---|---|
| rows | No | Number of citations to return | |
| bibcode | Yes | Paper identifier: bibcode, DOI, arXiv ID, or SciX ID (scix:...) | |
| response_format | No | markdown |
Changes observed during successful MCP inspections.
v1.3.0Input schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#"Input schema / properties / bibcode / descriptionPrevious value: -"SciX bibcode identifier"New value: +"Paper identifier: bibcode, DOI, arXiv ID, or SciX ID (scix:...)"Input schema / properties / bibcode / maxLengthAdded value: +200Input schema / properties / bibcode / minLengthAdded value: +1Input schema / properties / rows / descriptionPrevious value: -"Number of references to return (1-100, default 20)"New value: +"Number of citations to return"Input schema / properties / rows / maximumAdded value: +100Input schema / properties / rows / minimumAdded value: +1Input schema / properties / rows / typePrevious value: -"number"New value: +"integer"v1.0.14Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds no behavioral detail beyond that (no pagination, result limits, or auth notes), so it neither adds value nor contradicts the 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?
Two tightly written sentences with the core action front-loaded and the accepted identifier formats placed after. No filler or redundancy.
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?
For a simple read-only lookup the description is adequate, but with no output schema it omits what a result contains and ignores the rows (default 20, max 100) and response_format parameters entirely. An agent gets the gist but not the full call contract.
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?
Schema coverage is 67% and the listed identifier types ('bibcode, DOI, arXiv ID, or SciX ID') duplicate what the bibcode property description already says. The rows and response_format parameters get no mention in the description, so it adds no meaning beyond the schema.
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?
States a specific verb+resource ('Get papers referenced by a given paper') and adds the parenthetical '(backward citations)' which meaningfully clarifies direction. It implicitly separates itself from the sibling get_citations, though it never names that sibling explicitly.
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 'backward citations' phrasing implies when this applies versus forward citations, but no when-to-use/when-not guidance or named alternative (get_citations) is given. Usage is left to inference from the parenthetical.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.