Skip to main content
Glama

omniseek_graph

Read-only

Find how entities connect or what is known around a paper, author, or entity by querying a read-only, budgeted evidence graph with typed edges.

Instructions

Use WHEN you want HOW two entities connect, or what OmniSeek already knows AROUND a paper / author / entity; read-only, budgeted projections of its accumulated evidence graph with typed edges (ONE graph).

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

Pass view and args (that view's own parameters); a call with no view lists the views and their parameters. Views return node ids, labels and edge tuples, never content. find {label_query, kind?}: the entry point, a name to candidate node ids. stats {}: counts by kind, type and tier. neighborhood {anchor, depth? (<= 2), types?, policy?, max_nodes?}: the subgraph around a node. between {a, b, types?, policy?, max_nodes?}: up to 8 shortest connection paths. voices {doc_ids (<= 64), policy?}: collapse documents to distinct upstream voices. since {anchor, date, types?, max_nodes?}: stored edges added after a date. similar {anchor (a doc), k?}: vector-nearest document candidates, proposals only. policy: conservative (exact-id identity only, default) | working (plus your omniseek_ruling rulings) | exploratory (plus fuzzy candidates). A cut result carries capped: true; a failure returns an error dict. Entity kinds fill in as calls happen, so early emptiness is normal. Record identity with omniseek_ruling, relations with omniseek_statement. More: omniseek docs/TOOLS.md, omniseek_graph.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "omniseek_graph"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsNo
viewNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only supply readOnlyHint=true, but the description goes far beyond: results are "budgeted projections" returning "node ids, labels and edge tuples, never content", truncated results carry capped: true, failures return an error dict, entity kinds fill in over time so "early emptiness is normal", and the three policy tiers (conservative/working/exploratory) are defined including the default.

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-loaded with the trigger sentence, then a scannable indented view list with inline parameter signatures — every line carries information the schema does not. It is long, and the self-referential prefix/ToolSearch boilerplate plus the closing docs pointer are the least essential parts, but nothing is redundant filler.

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 covers returns explicitly (node ids, labels, edge tuples, never content), plus truncation, error behavior, policy defaults, and the sibling tools used to persist identity and relations. For a two-parameter dispatcher over seven views, an agent has everything needed to pick a view and call it 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 coverage is 0% and the schema is a bare {view, args} envelope, yet the description fully compensates by enumerating every view and its own argument set (label_query, kind?, anchor, depth? (<= 2), types?, policy?, max_nodes?, doc_ids (<= 64), a, b, k?, date) and explaining what args means. It also defines the policy enum values, which the schema does not.

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 specific capability up front: "Use WHEN you want HOW two entities connect, or what OmniSeek already knows AROUND a paper / author / entity." It explicitly scopes itself as read-only, budgeted projections of an evidence graph with typed edges, and separates itself from sibling write tools by directing identity recording to omniseek_ruling and relation recording to omniseek_statement.

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?

Gives an explicit trigger condition ("Use WHEN you want HOW two entities connect"), names the seven views with one-line selection semantics (find as "the entry point", between for "up to 8 shortest connection paths", similar as "proposals only"), and tells the agent what to do when the tool is absent (ToolSearch) or when no view is passed (lists views). Alternatives for the adjacent tasks are named directly.

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