Skip to main content
Glama

Explore an entity graph

get_entity_graph
Read-onlyIdempotent

One-hop graph from a typed ID: explicit catalogue links and derived co-occurrence with distinct-record counts and cited evidence. types filters neighbours before the bounds. Pass edge_id to page its evidence; pin snapshot_id across pages.

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": {
      "seed": "<seed>"
    },
    "name": "get_entity_graph"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedYes
limitNoEvidence page size, default 20, max 50
typesNo
offsetNo
edge_idNo
max_edgesNoDefault 50, max 200
max_nodesNoDefault 40, max 100
snapshot_idNo

Output Schema

NameRequiredDescriptionDefault
seedYes
countNo
edgesNo
nodesNo
typesNo
boundsNo
offsetNo
resultsNo
has_moreNo
truncatedNo
next_offsetNo
snapshot_idYes
total_edgesNo
total_matchesNo
effective_limitNo
neighbour_typesNo
requested_limitNo
requested_boundsNo
response_limitedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / types / items / enum
      Previous value: -[
      -  "person",
      -  "project",
      -  "section",
      -  "organisation",
      -  "location",
      -  "subject",
      -  "format",
      -  "language",
      -  "collection",
      -  "research_item",
      -  "publication",
      -  "journal",
      -  "podcast",
      -  "video",
      -  "playlist"
      -]New value: +[
      +  "person",
      +  "project",
      +  "section",
      +  "organisation",
      +  "location",
      +  "subject",
      +  "format",
      +  "language",
      +  "collection",
      +  "research_item",
      +  "publication",
      +  "journal",
      +  "podcast",
      +  "video",
      +  "chronicle",
      +  "playlist"
      +]
    • changedInput schema / properties / types / maxItems
      Previous value: -15New value: +16
    • addedOutput schema / properties / edges / items / properties / chronicle_count
      Added value: +{
      +  "type": "number"
      +}
    • changedOutput schema / properties / edges / items / required
      Previous value: -[
      -  "id",
      -  "source",
      -  "target",
      -  "kind",
      -  "relation",
      -  "count",
      -  "research_item_count",
      -  "publication_count",
      -  "video_count",
      -  "podcast_count",
      -  "evidence",
      -  "evidence_total"
      -]New value: +[
      +  "id",
      +  "source",
      +  "target",
      +  "kind",
      +  "relation",
      +  "count",
      +  "research_item_count",
      +  "publication_count",
      +  "video_count",
      +  "podcast_count",
      +  "chronicle_count",
      +  "evidence",
      +  "evidence_total"
      +]
    • changedOutput schema / properties / nodes / items / properties / type / enum
      Previous value: -[
      -  "person",
      -  "project",
      -  "section",
      -  "organisation",
      -  "location",
      -  "subject",
      -  "format",
      -  "language",
      -  "collection",
      -  "research_item",
      -  "publication",
      -  "journal",
      -  "podcast",
      -  "video",
      -  "playlist"
      -]New value: +[
      +  "person",
      +  "project",
      +  "section",
      +  "organisation",
      +  "location",
      +  "subject",
      +  "format",
      +  "language",
      +  "collection",
      +  "research_item",
      +  "publication",
      +  "journal",
      +  "podcast",
      +  "video",
      +  "chronicle",
      +  "playlist"
      +]
    • addedOutput schema / properties / requested_bounds
      Added value: +{
      +  "properties": {
      +    "max_edges": {
      +      "type": "number"
      +    },
      +    "max_nodes": {
      +      "type": "number"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Changed9 schema fields changed
    • removedInput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
    • removedOutput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
    • removedOutput schema / additionalProperties
      Removed value: -false
    • removedOutput schema / properties / bounds / additionalProperties
      Removed value: -false
    • removedOutput schema / properties / edges / items / additionalProperties
      Removed value: -false
    • removedOutput schema / properties / edges / items / properties / evidence / items / additionalProperties
      Removed value: -false
    • removedOutput schema / properties / neighbour_types / propertyNames
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / nodes / items / additionalProperties
      Removed value: -false
    • removedOutput schema / properties / results / items / additionalProperties
      Removed value: -false
  3. Changed3 schema fields changed
    • removedInput schema / properties / limit / maximum
      Removed value: -9007199254740991
    • removedInput schema / properties / max_edges / maximum
      Removed value: -9007199254740991
    • removedInput schema / properties / max_nodes / maximum
      Removed value: -9007199254740991
  4. Changed3 schema fields changed
    • addedInput schema / properties / types
      Added value: +{
      +  "items": {
      +    "enum": [
      +      "person",
      +      "project",
      +      "section",
      +      "organisation",
      +      "location",
      +      "subject",
      +      "format",
      +      "language",
      +      "collection",
      +      "research_item",
      +      "publication",
      +      "journal",
      +      "podcast",
      +      "video",
      +      "playlist"
      +    ],
      +    "type": "string"
      +  },
      +  "maxItems": 15,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • addedOutput schema / properties / neighbour_types
      Added value: +{
      +  "additionalProperties": {
      +    "type": "number"
      +  },
      +  "propertyNames": {
      +    "type": "string"
      +  },
      +  "type": "object"
      +}
    • addedOutput schema / properties / types
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  5. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the description is free to add the parts that matter: edges come in two flavours (explicit vs derived), carry distinct-record counts and cited evidence, and snapshot_id provides a consistent view across paginated calls. That is real behavioral context beyond the annotations, with only the cost/scale characteristics of large traversals left unstated.

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?

Three dense sentences with the core concept front-loaded and the parameter hints following. The telegraphic phrasing ('types filters neighbours before the bounds') is efficient, though slightly clipped enough to require 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?

For an 8-parameter graph traversal with an output schema already documenting the return shape, the description covers the essentials: what is traversed, what the edges contain, how filtering applies, and how to paginate consistently. Nothing an agent needs in order to make a correct first call is missing.

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

Parameters3/5

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

Schema coverage is 38% across 8 parameters, so the description needs to compensate and does so for three of them: types (applied to neighbours before the bounds, an important ordering semantic), edge_id (pages that edge's evidence), and snapshot_id (pinning for stable pagination). It leaves seed, limit, offset, max_edges, and max_nodes largely to the schema — 'typed ID' hints at the seed's accepted identifier types but never enumerates them, and the interaction between max_edges/max_nodes and limit is never explained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific operation and resource: a one-hop graph traversal from a typed ID, returning both explicit catalogue links and derived co-occurrence with counts and cited evidence. That is far more precise than a generic 'get graph' and implicitly separates it from sibling lookups like find_related or get_similar_items, though it never names an alternative explicitly.

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

Usage Guidelines3/5

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

The description gives operational guidance — filter neighbours with types, page evidence with edge_id, pin snapshot_id across pages — but it is framed entirely around how to drive the parameters rather than when to choose this tool over resolve_entity, find_related, or get_semantic_map. No when-not or prerequisite guidance is offered.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.