agent-memory-mcp

graph_neighbors

Read-onlyIdempotent

Explore an entity's graph neighborhood by traversing incoming and outgoing relationships up to depth 3, applying node/edge limits and optional time filters to return bounded, relevant connections.

Instructions

Bounded BFS up to depth 3 with node/edge limits and temporal filters; reports truncation.

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": {
      "entity_id": "<entity_id>"
    },
    "name": "graph_neighbors"
  }
}

Input Schema

Name	Required	Default
`at`	No
`project`	No
`direction`	No	both
`entity_id`	Yes
`max_depth`	No
`max_nodes`	No
`namespace`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.1Sep 9, 2026

TDQS

A3.9/5.0

Behavior4/5

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

The description mentions reporting truncation, which is a concrete behavioral detail. Combined with annotations (readOnlyHint, idempotentHint, destructiveHint), it provides good transparency about side effects and outcome reporting. However, it does not explain edge cases like empty results or error handling.

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 a single, compact sentence with no superfluous words. It front-loads the core behavior (bounded BFS) and then specifies constraints and reporting, making it optimally concise yet informative.

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

Completeness4/5

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

For a graph traversal tool, the description covers key aspects: traversal type, depth bound, limits, temporal filtering, and truncation reporting. It does not specify the exact output format (e.g., whether nodes, edges, or both are returned), but given the simplicity and common patterns, this is a minor gap.

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

Parameters2/5

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

Schema description coverage is 0%, and the description does not clarify parameter meanings. While names like entity_id, max_depth, and max_nodes are self-explanatory, others like project, namespace, and at are ambiguous without elaboration. The tool description fails to compensate for the lack of schema documentation.

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 clearly states the tool performs a bounded BFS up to depth 3 with node/edge limits and temporal filters, and reports truncation. This unambiguously conveys its primary function of traversing graph neighbors, distinguishing it from sibling tools like graph_path which focus on pathfinding.

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 does not explicitly state when to use this tool versus alternatives (e.g., graph_path or memory_search). While the name and behavior imply use for neighbor exploration with constraints, there is no direct guidance on selection criteria, leaving some inference required.

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