Skip to main content
Glama

Novel Archive Management

manage_archive
Destructive

Export, import, archive, unarchive, clone, branch, and checkpoint Novel save files for backup, sharing, branching, or restoring campaign state.

Instructions

Export, import, archive, unarchive, clone, branch, and checkpoint Novel save files. export writes a file in json or markdown; share emits a portable full-scope json bundle with embedded adventure content; import writes Novel state and mode selects dry-run (validate only), merge (keep existing entries), or replace (discard current Novel state), while strict aborts on unresolved references. clone copies the whole Novel unless trim_audit_sessions keeps only recent sessions; branch starts from from_event (default latest); archive is reversible with unarchive; checkpoint_restore replaces the live Novel with the stored checkpoint and is itself undoable; checkpoint subscriptions persist. Use when: exporting or importing a Novel, archiving/unarchiving, cloning/branching, or managing checkpoints. Do NOT use when: creating, resuming, renaming, or ending a Novel — use manage_novel. Revert the most recent mutation with manage_history (action: undo); checkpoint_list is read-only.

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": {
      "action": "<action>"
    },
    "name": "manage_archive"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataNoExported Novel JSON (import).
modeNodry-run, merge, or replace (import).
slugNoNovel slug (resume/switch/archive/unarchive/info).
labelNoCheckpoint label (checkpoint_set/list/restore/remove).
scopeNoExport scope (export).
shareNoEmit a portable full-scope bundle with embedded adventure content (export; JSON only).
actionYesexport, import, archive, unarchive, clone, branch, checkpoint_set, checkpoint_list, checkpoint_restore, checkpoint_remove.
formatNoOutput format (export).
strictNoFail on any cross-reference mismatch (import).
new_nameNoName for the copy or branch (clone/branch).
from_eventNoEvent-log ordinal to branch from (branch; default latest).
source_slugNoNovel to copy or branch from (clone/branch).
include_checkpointsNoInclude checkpoints in export (default false; export).
trim_audit_sessionsNoKeep only the most recent N sessions' audit entries in the clone (clone; default full copy).

Output Schema

NameRequiredDescriptionDefault
textNoHuman-readable text envelope mirroring the structured result (REQ-001, REQ-548a).
statusYesMachine-readable result status: OK, NEED_INPUT, WARNING, PARTIAL, or an error category (REQ-002, REQ-548c).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2026.10.18
    • addedInput schema / properties / share
      Added value: +{
      +  "description": "Emit a portable full-scope bundle with embedded adventure content (export; JSON only).",
      +  "type": "boolean"
      +}
  2. Changed14 schema fields changedv2026.10.13
    • removedInput schema / properties / codex_adventure
      Removed value: -{
      -  "description": "Codex adventure to seed from (create).",
      -  "type": "string"
      -}
    • removedInput schema / properties / current_scene
      Removed value: -{
      -  "description": "Current-scene summary (save_context).",
      -  "type": "string"
      -}
    • removedInput schema / properties / description
      Removed value: -{
      -  "description": "Description (create/description).",
      -  "type": "string"
      -}
    • removedInput schema / properties / detail
      Removed value: -{
      -  "description": "Return full metadata (list).",
      -  "type": "boolean"
      -}
    • removedInput schema / properties / filter
      Removed value: -{
      -  "description": "active, archived, or all (list).",
      -  "enum": [
      -    "active",
      -    "archived",
      -    "all"
      -  ],
      -  "type": "string"
      -}
    • removedInput schema / properties / genre
      Removed value: -{
      -  "description": "Genre tag (create/genre).",
      -  "type": "string"
      -}
    • removedInput schema / properties / immediate_situation
      Removed value: -{
      -  "description": "Immediate situation (save_context).",
      -  "type": "string"
      -}
    • removedInput schema / properties / long_term_plans
      Removed value: -{
      -  "description": "Long-term plans (save_context).",
      -  "type": "string"
      -}
    • removedInput schema / properties / name
      Removed value: -{
      -  "description": "Novel name (create).",
      -  "type": "string"
      -}
    • removedInput schema / properties / new_slug
      Removed value: -{
      -  "description": "New slug (rename).",
      -  "type": "string"
      -}
    • removedInput schema / properties / pending_player_action
      Removed value: -{
      -  "description": "Pending player action (save_context).",
      -  "type": "string"
      -}
    • removedInput schema / properties / player_goals
      Removed value: -{
      -  "description": "Player goals (save_context).",
      -  "type": "string"
      -}
    • removedInput schema / properties / ruleset
      Removed value: -{
      -  "description": "Ruleset slug (create).",
      -  "type": "string"
      -}
    • removedInput schema / properties / short_term_plans
      Removed value: -{
      -  "description": "Short-term plans (save_context).",
      -  "type": "string"
      -}
  3. Added

TDQS

A4.6/5.0
Behavior4/5

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

Beyond the annotations (destructiveHint=true), it discloses what is actually lost or preserved: replace discards current Novel state, merge keeps existing entries, strict aborts on unresolved references, trim_audit_sessions keeps only recent sessions, and archive/checkpoint_restore are reversible or undoable. The one blur is 'share emits a portable full-scope json bundle', which reads like an action even though share is a boolean export modifier.

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?

Purpose is front-loaded in the first sentence and the when/when-not routing closes it, so structure is sound. The middle is a dense semicolon chain covering ten actions, which is justified by the tool's breadth but makes a few clauses (notably the share clause) harder to parse than necessary.

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

Completeness5/5

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

For a ten-action, fourteen-parameter tool, the description covers every mutating action's semantics, reversibility, and abort conditions; an output schema exists so return values need not be described. Nothing an agent needs to pick an action or predict side effects is missing.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3; the description earns above baseline by explaining what the enum values actually do (dry-run validate only, merge, replace) and by clarifying strict, trim_audit_sessions, and from_event's default. It leaves slug, label, scope, format, and include_checkpoints to the schema.

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 opening sentence names the resource (Novel save files) and enumerates the exact operations (export, import, archive, unarchive, clone, branch, checkpoint). It then defines each action's effect concretely, and explicitly separates itself from manage_novel for Novel lifecycle operations, so an agent can route correctly without opening the schema.

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

Usage Guidelines5/5

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

Explicit 'Use when' and 'Do NOT use when' blocks name the sibling tools to use instead (manage_novel for create/resume/rename/end, manage_history action: undo for reverting a mutation). It also flags checkpoint_list as read-only, giving action-level guidance that the tool-level annotations cannot express.

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