Skip to main content
Glama

Get relation subgraph

mcai_related
Read-onlyIdempotent

Retrieves the relation subgraph around a concept, including derived links, to explain causal, structural, or hierarchical connections and answer how terms relate or which parents and children exist.

Instructions

Get the relation subgraph around a concept (including derived relations) to explain causal, structural, or hierarchical links. Use for questions such as "How are A and B related?" or "What are this concept's parents and children?". Routing: full entry -> mcai_concept; full-sentence explanation -> mcai_answer; finding a term -> mcai_search. Boundary: returns only relations registered in the base and states explicitly when none exist.

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": {
      "term": "<term>"
    },
    "name": "mcai_related"
  }
}

Input Schema

NameRequiredDescriptionDefault
termYesCentral term; must be a term in the base, e.g. 元意识 / 序生智能体; use mcai_search first if unsure.
depthNoRelation depth: 1 for direct relations, 2 for two hops; default 1.
include_mentionsNoInclude weak co-occurrence ('mention') edges. Default false returns only curated core/derived relations; set true to include mention edges.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.7
    • addedInput schema / properties / include_mentions
      Added value: +{
      +  "default": false,
      +  "description": "Include weak co-occurrence ('mention') edges. Default false returns only curated core/derived relations; set true to include mention edges.",
      +  "type": "boolean"
      +}
  2. Changed2 schema fields changedv0.1.5
    • changedInput schema / properties / depth / description
      Previous value: -"关系展开深度:1 只取直接关系,2 取两跳;默认 1。"New value: +"Relation depth: 1 for direct relations, 2 for two hops; default 1."
    • changedInput schema / properties / term / description
      Previous value: -"中心术语名,必须是库内已收录的术语,例如 元意识 / 序生智能体;不确定时先用 mcai_search。"New value: +"Central term; must be a term in the base, e.g. 元意识 / 序生智能体; use mcai_search first if unsure."
  3. Changed3 schema fields changedv0.1.2
    • changedInput schema / properties / depth / description
      Previous value: -"关系展开深度:1 只取直接关系,2 取两跳;默认 1"New value: +"关系展开深度:1 只取直接关系,2 取两跳;默认 1。"
    • changedInput schema / properties / term / description
      Previous value: -"中心术语名,例如 元意识 / 序生智能体"New value: +"中心术语名,必须是库内已收录的术语,例如 元意识 / 序生智能体;不确定时先用 mcai_search。"
    • addedInput schema / properties / term / examples
      Added value: +[
      +  "元意识",
      +  "序生智能体"
      +]
  4. Changed3 schema fields changedv0.1.1
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / depth / description
      Added value: +"关系展开深度:1 只取直接关系,2 取两跳;默认 1"
    • addedInput schema / properties / term / description
      Added value: +"中心术语名,例如 元意识 / 序生智能体"
  5. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already establish that this is a safe, read-only, idempotent operation. The description adds valuable behavioral context: derived relations are included, only base-registered relations are returned, and the tool explicitly states when no relations exist. It does not discuss return shape/pagination, but for a read-only relation lookup the disclosure is adequate.

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 dense and front-loaded: purpose first, then concrete usage examples, then explicit routing and boundary. Every sentence adds decision-relevant information with no 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?

For a read-only relation-subgraph tool with no output schema, the description supplies the missing pieces an agent needs: when to use it, how it differs from siblings, the inclusion of derived relations, and the explicit no-relations boundary. All three parameters are already fully specified in the schema.

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 100%, so the schema already documents term, depth, and include_mentions in detail. The description reinforces derived relations and the term context but does not add syntax, edge cases, or meaning beyond the schema.

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 verb and resource ('Get the relation subgraph around a concept'), clarifies that derived relations are included, and explains the kind of links returned. This clearly distinguishes it from sibling tools that fetch concepts, answers, lists, or search results.

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?

Provides concrete question patterns ('How are A and B related?', 'What are this concept's parents and children?') and an explicit routing table to mcai_concept, mcai_answer, and mcai_search. It also defines a boundary: only registered relations are returned and absence is reported explicitly.

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