Skip to main content
Glama
Battam1111

omniseek

by Battam1111
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

omniseek_resolve_identity

Resolve a person's name to ranked candidate author IDs, returning options for disambiguation instead of guessing. Use a known paper, hint, or institution to pin the correct author before mapping their connections.

Instructions

Resolve a PERSON's name to candidate author ids — the shared front door for EVERY relationship layer (you must know WHICH person before you can map their connections).

Fully-qualified MCP name: mcp__omniseek__omniseek_resolve_identity (server name is omniseek; there is no omniseek-eye server).

OmniSeek's other tools keyword-search PAPERS; this resolves an AUTHOR. It NEVER silently picks — it returns ranked CANDIDATES so YOU disambiguate (the homonym trap: "Zhennan Shen" is three different people in OpenAlex). hint (e.g. an institution like "HKUST", or a field) only RE-ORDERS candidates, never filters them. source: "auto" (OpenAlex first, pulls in Semantic Scholar when the top OpenAlex hit is sparse — i.e. a likely junior / arXiv-frontier author OpenAlex hasn't indexed), "openalex", or "s2".

paper (an arXiv id / DOI / title of a KNOWN paper by this person) is the reliable way to pin a COMMON-NAME JUNIOR — it resolves straight from the paper's author list, where a bare name search fails (e.g. many distinct researchers share a common name like "Wei Zhang"; their paper fixes the exact id).

Use the returned id with omniseek_coauthors. ambiguous: true means two comparable candidates — confirm with a hint / a paper / a known co-author before trusting either.

likely_same_person (when present) groups same-name same-backend candidates that are likely ONE person SPLIT across ids, with a ready-to-paste merge_token ("A123+A456") you can hand straight to omniseek_coauthors as one input; it never auto-merges, just surfaces the candidate merge.

Returns: {query, source, candidates:[{id, source, name, works_count, cited_by, institution, via_paper?}], ambiguous, note, likely_same_person?:[{source, ids, name, merge_token, note}], degraded?:{openalex}}. degraded (when present) means the OpenAlex lookup FAILED (rate-limited / upstream down): an empty/thin result is then missing-data, NOT a confirmed "not in the graph" — retry, or pass source='s2' / paper=.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hintNo
nameYes
paperNo
sourceNoauto

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A5/5.0
Behavior5/5

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

With no annotations provided, the description fully carries the behavioral transparency burden. It discloses that the tool never silently picks, that hint only re-orders and never filters, that likely_same_person never auto-merges, and that degraded means missing-data rather than a confirmed absence. This is far more than a typical tool description provides.

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?

The description is long but deliberately information-dense; every paragraph adds actionable guidance rather than filler. It is front-loaded with the core purpose and distinct identity, then layers details about parameters, disambiguation, merge tokens, and degraded behavior in a logical order.

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 a tool with no output schema and no annotations, the description is exceptionally complete. It documents the full return shape, explains ambiguous and degraded response fields, provides retry strategies, and ties the output into the broader coauthors workflow. An agent has everything needed to select and invoke the tool correctly.

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 must compensate, and it does. Every parameter is explained with meaningful semantics: hint's re-order-only behavior, source's three modes and 'auto' logic, paper's role in resolving common-name authors, and name as the required person to resolve.

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 uses a specific verb ('Resolve') and resource ('a PERSON's name to candidate author ids'), and immediately distinguishes itself from sibling tools: 'OmniSeek's other tools keyword-search PAPERS; this resolves an AUTHOR.' It also frames the tool as the 'shared front door for EVERY relationship layer,' making its role unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly says when to use this tool versus alternatives: paper search is for papers, this is for authors, and the result should feed omniseek_coauthors. It also gives concrete conditional guidance: use hint to re-order, use paper to pin common-name juniors, verify ambiguous candidates, and pass source='s2' or paper= when degraded.

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

Deploy Server

Other Tools