Skip to main content
Glama

omniseek_coauthors

Read-only

Find who a researcher collaborates with: rank co-authors by joint papers, map author-group connections and shared bridge collaborators for one or more authors.

Instructions

Use WHEN you want WHO a researcher collaborates with: advisor + closest collaborators by joint-paper count, or how a paper's author group is connected (WebSearch cannot build this). One LAYER, not the whole graph: co-authorship is one edge type; the other layers, and what each tie means, are yours.

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

Args: authors: names, ids (omniseek_resolve_identity) or "id1+id2" for one person split across ids. source: "openalex" (default) or "s2". hints: per-author disambiguation hints, parallel to authors. papers: per-author known papers, parallel to authors.

One author: their coauthors ranked by joint papers. Several: also the pairwise joint-paper edges among them and the bridge collaborators shared by two or more. Returns {source, n_authors, nodes: [{query, resolved, ambiguous, alternatives, works_seen, top_coauthors: [{id, name, joint}], degraded?}], edges: [{a, b, joint_count, papers}], bridges: [{id, name, shared_by, total_joint}], cooc: [{a, b, n}], degraded?}. degraded = the lookup failed: an empty graph is missing data to retry, not "no collaborators". More: omniseek docs/TOOLS.md, omniseek_coauthors.

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": {
      "authors": "<authors>"
    },
    "name": "omniseek_coauthors"
  }
}

Input Schema

NameRequiredDescriptionDefault
hintsNo
papersNo
sourceNoopenalex
authorsYes

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?

With readOnlyHint=true already declaring a safe read, the description adds genuinely non-obvious behavior: the `degraded` flag means the lookup failed, so an empty graph is missing data to retry rather than a genuine "no collaborators" result. It also discloses the source choices (openalex default vs s2) and the full return shape, though it says nothing about rate limits, coverage differences between sources, or size limits on the graph.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The WHEN-first opening and the Args/Returns block are well front-loaded and scannable, but the definition also carries delivery boilerplate ("your MCP config adds its own prefix; never guess one. Not in your tool list? ToolSearch ...") that consumes space without describing the tool's semantics. The prose is dense and compressed to the point that some clauses, like "the other layers ... are yours," need a second read.

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?

There is no output schema, and the description compensates by enumerating the returned fields (nodes, top_coauthors, edges, bridges, cooc, degraded) and explaining what each mode produces. For a four-parameter analytical tool, an agent has enough to choose it, format the call, and interpret the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden and does: `authors` accepts names, ids, or "id1+id2" for one person split across ids; `source` is openalex by default with s2 as the alternative; `hints` and `papers` are both per-author and parallel to the authors array. All four parameters gain meaning that the bare schema titles do not convey.

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?

The description opens with a specific verb-plus-resource framing: "Use WHEN you want WHO a researcher collaborates with: advisor + closest collaborators by joint-paper count, or how a paper's author group is connected." It explicitly scopes itself to one edge type ("One LAYER, not the whole graph"), which separates it from the broader graph sibling, and notes that WebSearch cannot produce this.

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?

The "Use WHEN" clause gives a clear triggering context, and it distinguishes single-author mode from multi-author mode (pairwise edges plus bridge collaborators) so an agent knows which shape of call yields which answer. It points to omniseek_resolve_identity for ids, but never names the graph tool as the alternative for other relationship layers, only hints at it via "the other layers ... are yours."

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