Skip to main content
Glama
Sign In
AIWorkhub

AIWorkhub

by shrec
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

aiworkhub_manager_context_graph_related

Read-only

Retrieve bounded, deterministic relations for a single context graph node by node ID, returning newest source events first up to a specified limit.

Instructions

MANAGER READ: retrieve bounded deterministic relations for one graph node.

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": {
      "node_id": "<node_id>"
    },
    "name": "aiworkhub_manager_context_graph_related"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum relations to return, newest source event first; default 20, clamped to 1-50.
node_idYesContext Graph node id to list relations for, non-blank, at most 512 bytes.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.12.67
    • addedInput schema / properties / limit / description
      Added value: +"Maximum relations to return, newest source event first; default 20, clamped to 1-50."
    • addedInput schema / properties / node_id / description
      Added value: +"Context Graph node id to list relations for, non-blank, at most 512 bytes."
  2. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds that results are 'bounded' and 'deterministic', which hints at stable ordering and clamping, but does not state ordering semantics, emptiness behavior, or whether relations are one-hop or transitive.

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 front-loaded sentence with no filler; the operation type is the first token. It is arguably over-compressed for a tool with several closely named siblings, but nothing is wasted.

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?

An output schema exists and the input schema is fully documented, so return values and argument formats need no explanation. What is missing is disambiguation from the crowded context_graph_* and *_related family, which is the main thing an agent must resolve before calling.

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 description coverage is 100%, with both node_id (non-blank, ≤512 bytes) and limit (default 20, clamped 1-50, newest source event first) fully documented in the schema. The description adds no parameter meaning beyond that, so baseline 3 applies.

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 verb and resource: retrieve relations for one graph node, with the qualifiers 'bounded' and 'deterministic'. It does not name or contrast with sibling readers such as context_graph_search, context_graph_range, or ai_memory_related, so an agent has to infer the distinction from the name alone.

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 'MANAGER READ' prefix signals this is a read-side manager operation, and 'one graph node' implies you already have a node id. There is no explicit when-to-use/when-not, and no mention of when to prefer context_graph_search (query-driven) over this node-id-driven lookup.

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

Deploy Server

Other Tools