Skip to main content
Glama

Ingest Hosts to Knowledge Graph

tunnel_ingest_hosts
Read-onlyIdempotent

Lists managed SSH hosts and ingests them into the medulla knowledge graph as typed Host, HostGroup, and SshKey nodes, optionally attaching them to a specified host group.

Instructions

List the managed SSH inventory and push it into the medulla KG.

Maps each alias → a typed :Host node (+ :HostGroup / :SshKey and their :inGroup / :usesKey links). Best-effort: no-ops cleanly when no KG engine is reachable.

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": "tunnel_ingest_hosts"
  }
}

Input Schema

NameRequiredDescriptionDefault
groupNoHostGroup name to attach the ingested hosts to.all

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.1

TDQS

B3.3/5.0
Behavior2/5

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

The description adds real behavior — the exact node and link types created and best-effort no-op semantics — which is useful beyond the annotations. However, it describes creating and linking records in a knowledge graph while annotations declare readOnlyHint=true, so an agent told this is a pure read may not expect graph state to be written. The idempotentHint=true and destructiveHint=false claims are consistent with the 'best-effort' framing.

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?

Two short sentences with the action front-loaded and the node-mapping detail in a compact parenthetical block. No filler, though the backslash-escaped formatting is slightly noisy for an agent-facing string.

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?

With one optional parameter at full schema coverage, an output schema, and annotations present, the description supplies what remains: what gets created in the graph and how failure is handled. The only completeness gap is the unresolved read-vs-write framing against readOnlyHint.

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% and the single 'group' parameter is documented inline as the HostGroup to attach ingested hosts to. The description mentions ':HostGroup' and ':inGroup' but does not add meaning about the parameter beyond what the schema already says, so the high-coverage baseline of 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 compound action: read the managed SSH inventory and write typed ':Host' nodes plus ':HostGroup'/':SshKey' nodes and ':inGroup'/':usesKey' links into the medulla KG. That mapping detail makes it distinguishable from a plain listing tool like tunnel_manager_list_hosts, though no sibling is named 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?

Usage is implied rather than stated: an agent can infer this is the tool for populating the KG from inventory, and 'no-ops cleanly when no KG engine is reachable' tells it the call is safe to attempt. There is no explicit when-not guidance or pointer to the inventory-listing/loading siblings for the read-only case.

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