Skip to main content
Glama
Sign In
Archiware MCP

Archiware MCP

by mnott
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

pack

Creates resumable tar archives from a P5 host source directory, records every file in the catalogue, and previews the plan before confirmation.

Instructions

Packs a source directory on the P5 host into tar files (D2D2T) and records every file in the catalogue. Without confirm: only the plan (walks the source once at low I/O priority; tar names, sizes, file counts, time estimate). With confirm:true: writes the tars (tar --sort=inode, resumable per tar via .done markers, sha256 per tar, plain-text listing next to each tar) and the rows in one transaction per tar. Long-running (hours for TB-sized sets); does not hold the nsdchat lock.

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": {
      "source": "<source>",
      "set": "<set>"
    },
    "name": "pack"
  }
}

Input Schema

NameRequiredDescriptionDefault
maxNoMax tar size, e.g. 50G (default 50G)
setYesSet name (letters, digits, . _ -)
intoNoPack root (default config packRoot); tars go to <root>/<set>/
detachNoRun the whole plan as one self-contained runner on the P5 host (setsid nohup, resumable per tar, log in the tar dir); returns at once, the client may disconnect; follow with pack_status
replanNoIgnore a stored plan of an interrupted run
sourceYesAbsolute source directory on the P5 host
confirmNoMust be true to actually run; without it only the plan/commands are returned

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations supplied, the description carries the whole burden and does so well: it discloses the low-I/O-priority source walk, tar --sort=inode ordering, per-tar resumability via .done markers, sha256 per tar, plain-text listings, one catalogue transaction per tar, and that it does not hold the nsdchat lock. The main omissions are failure/partial-success behavior and permission requirements.

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?

It is dense but front-loaded: the core action comes first, then the confirm/no-confirm split, then runtime traits. Parenthetical detail is heavily compressed but every clause carries information; a sentence break instead of parentheses would improve scanability slightly.

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 seven-parameter, no-output-schema, no-annotation mutation tool, it covers the essentials: plan vs execute, resumability, long runtime, and lock behavior. What is missing is a description of what the plan response actually contains and how errors or interrupted runs surface, which matters for a multi-hour operation.

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%, so the schema already explains all seven parameters. The description adds real meaning only for 'confirm' (its gate semantics) and slightly for 'detach' (follow with pack_status); 'max', 'into', 'set', and 'replan' get no additional context beyond the schema, 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?

The description states a specific verb and resource ('Packs a source directory on the P5 host into tar files') plus the important side effect of recording files in the catalogue. It is clear what the tool does, though it never explicitly distinguishes itself from the sibling 'plan' or 'dryrun_plan' tools, leaving the agent to infer the difference.

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

Usage Guidelines4/5

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

It gives a clear conditional usage rule: without 'confirm' you get only a plan, with confirm:true it writes tars and catalogue rows. That is strong when-to-use guidance for the safe/unsafe split. It does not name an alternative tool to use for the plan-only path, so the agent must guess whether a sibling exists for that.

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