Skip to main content
Glama
蓝汐 · 潮汐认知图谱

蓝汐 · 潮汐认知图谱

by A16Nights

cg_graph

Fetches a centered or layer-filtered subgraph of related memory nodes and edges so you can inspect how concepts connect.

Instructions

获取记忆关系子图(以某节点为中心或按层级返回关联度最高的节点和边)。

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": "cg_graph"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo最大节点数,默认 50
layersNo
centerIdNo可选中心节点 ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.4/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It discloses read semantics ('获取') and that results are ordered/selected by relevance ('关联度最高'), but says nothing about pagination, how limit interacts with layers, whether centerId and layers can combine, or what the default mode is.

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?

A single sentence with the verb and resource front-loaded, and the two modes compactly bracketed. It is dense but waste-free, though the parenthetical could have been split for easier scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-parameter, annotation-free tool with no output schema, the description covers what is returned (nodes and edges) and the two query modes, which is the minimum viable. It leaves gaps on defaults, how limit bounds the result, and how the layer enum values should be chosen.

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 67%: limit and centerId are already documented in the schema, while the layers array has only an enum and no description. The description partially compensates by explaining layer-based top-relevance selection, but never defines the individual layer values (anchor, self, structural, knowledge, episodic, goals, unresolved) or precedence when both centerId and layers are given.

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?

The description gives a specific verb+resource ('获取记忆关系子图') and clarifies the two retrieval forms (centered on a node, or layer-based top-relevance nodes and edges). An agent can tell this is a graph/subgraph reader rather than a text recall tool, though no sibling (e.g. cg_recall, cg_read) is named to sharpen the distinction.

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?

Usage is only implied through the two bracketed modes: '以某节点为中心' signals the centerId path and '按层级' signals the layers path. There is no explicit guidance on when to choose this over cg_recall or cg_read, and no stated prerequisites or exclusions.

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