Skip to main content
Glama

omniseek_paper_recommend

Read-only

Find semantically similar papers from seed arXiv IDs, DOIs, or S2 IDs to surface related work that keyword search and citation graphs miss, including very recent publications.

Instructions

Use WHEN you have a paper and want more like it: semantically-similar papers (SPECTER embeddings) that keyword search and the citation graph miss, including very recent work.

Tool name: omniseek_paper_recommend (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_paper_recommend".

Args: ids: seed paper ids: arXiv ids, DOIs or S2 ids (for an openalex hit, metadata.paper_id or metadata.doi, not the W-id). limit: how many papers.

Returns {seeds, n, papers: [{id, title, year, date, cited_by, first_author, doi, url}]} in S2 relevance order. More: omniseek docs/TOOLS.md, omniseek_paper_recommend.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "ids": "<ids>"
    },
    "name": "omniseek_paper_recommend"
  }
}

Input Schema

NameRequiredDescriptionDefault
idsYes
limitNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true, and the description adds real behavior beyond that: the embedding-based similarity model, inclusion of very recent work, and the fact that results come back in S2 relevance order. It also states the seed-vs-result relationship via the seeds field. It stops short of noting rate limits, seed failure behavior, or empty-result handling.

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?

Front-loads the trigger condition, then structures Args and Returns as labeled blocks, which is easy to scan. Some lines are environment boilerplate (the MCP prefix warning, the ToolSearch fallback, the docs pointer with the tool name repeated) that do not help an agent decide to invoke the tool.

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 no output schema, the description supplies the return shape explicitly ({seeds, n, papers: [...]}) and names the ordering guarantee, which is exactly what an agent needs to consume results. Combined with the id-format guidance for a 0%-coverage schema, nothing essential is missing for correct invocation.

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 0%, so the description carries the full burden and mostly does: ids is explained as arXiv ids, DOIs, or S2 ids, with a specific caveat about using metadata.paper_id or metadata.doi (not the W-id) for openalex hits. limit is only glossed as 'how many papers' with no default or max disclosed, which is the one weak spot.

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 concrete verb and resource ('recommend semantically-similar papers') and pins the mechanism: SPECTER embeddings, contrasted explicitly against keyword search and the citation graph. An agent can tell this apart from omniseek_search or omniseek_graph based on the description alone.

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?

Opens with an explicit when-to-use trigger ('WHEN you have a paper and want more like it') and explains the gap it fills versus keyword search and the citation graph, including coverage of very recent work. It does not name a specific sibling (e.g. omniseek_paper_enrich) to route away from, so selection among the omniseek_paper_* family is still partly inferred.

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