Skip to main content
Glama

Mesh Bootstrap

tm_inventory_mesh_bootstrap

Bootstrap mesh inventory by running bulk SSH command, file, and key operations across YAML host groups; preview resolved hosts before execution or target one host safely.

Instructions

Mesh bootstrap (tm_inventory). Bulk inventory operations against YAML host groups.

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": "tm_inventory_mesh_bootstrap"
  }
}

Input Schema

NameRequiredDescriptionDefault
cfgNoLocal SSH config path (copy_ssh_config).
cmdNoShell command (run_command).
keyNoShared key path (configure_key_auth)./app/.ssh/id_ed25519
hostNorun_command only. Optional single-host alias to target instead of the whole 'group' fan-out — the safe way to reach ONE inventory host (e.g. 'gb10') without running against 'homelab'. Resolved and authorized through the same alias store tm_remote/tm_hosts use, so the two are one source of truth: an unknown or unauthorized alias is rejected outright, never silently skipped. Takes precedence over 'group' when set.
groupNoTarget group.all
lpathNoLocal file path (send_file).
rpathNoRemote file path (send_file/receive_file).
key_pfxNoPrefix for new keys (rotate_key)./root/.ssh/id_
previewNorun_command only. If true, resolve the exact target host(s) for 'host'/'group' and return them in 'resolved_hosts' WITHOUT running 'cmd' — lets a caller verify scope before executing for real (no surprise fan-out). The real (non-preview) response also always includes 'resolved_hosts' for the same reason.
rmt_cfgNoRemote config path (copy_ssh_config)./root/.ssh/config
timeoutNoCommand timeout in seconds.
key_typeNoKey type: rsa or ed25519.ed25519
parallelNoRun parallel.
inventoryNoYAML inventory path (default: $XDG_CONFIG_HOME/scion-sdk/inventory.yml)./root/.config/scion-sdk/inventory.yml
max_threadsNoMax threads.
lpath_prefixNoLocal dir prefix (receive_file).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv3.4.7
    • changedInput schema / properties / inventory / default
      Previous value: -"/root/.config/agent-connectors/inventory.yml"New value: +"/root/.config/scion-sdk/inventory.yml"
    • changedInput schema / properties / inventory / description
      Previous value: -"YAML inventory path (default: $XDG_CONFIG_HOME/agent-connectors/inventory.yaml)."New value: +"YAML inventory path (default: $XDG_CONFIG_HOME/scion-sdk/inventory.yml)."
  2. Addedv3.3.1

TDQS

C2.3/5.0
Behavior2/5

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

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, so the agent knows it is a non-idempotent open-world write. The description adds nothing: it never states that this connects over SSH to remote hosts, executes shell commands, writes remote file paths, or rotates keys — all behaviors implied only by parameter names. It also fails to surface the built-in preview/resolved_hosts safeguard, which is exactly the kind of behavioral context the description should carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short fragments with no filler, so it is certainly concise, but the brevity is achieved by omitting the essential information rather than by tight editing. The leading term 'Mesh bootstrap' is front-loaded yet conveys almost nothing to an uninformed agent.

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

Completeness2/5

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

For a 16-parameter, zero-required, multi-mode dispatcher that reaches real remote hosts, two fragments are far from sufficient — the mode/parameter mapping and target-scoping model exist only in the schema. The presence of an output schema excuses the description from explaining return values, but nothing else.

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 parameter descriptions are unusually rich — they name which operation each parameter belongs to, spell out host-alias resolution and precedence, and explain the preview behavior. The description contributes no additional parameter meaning, which is acceptable given the schema carries the full burden, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description is 'Mesh bootstrap (tm_inventory). Bulk inventory operations against YAML host groups.' — 'mesh bootstrap' is an opaque label, and 'bulk inventory operations' does not say what the tool actually does. Critically, the schema reveals this single tool is a mode dispatcher covering six distinct operations (run_command, send_file, receive_file, copy_ssh_config, rotate_key, configure_key_auth), each of which also exists as its own sibling tool, and the description never mentions this. An agent cannot distinguish it from tm_inventory_run_command or tm_inventory_send_file by reading the description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of alternatives, and no explanation of why one would pick this multi-operation entry point over the single-purpose tm_inventory_* siblings. The only usage hint anywhere ('run_command only', 'safe way to reach ONE inventory host') lives in individual parameter descriptions rather than the tool description.

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