Skip to main content
Glama

Import a finished download

import_download

Imports a finished download the *arr left stuck at importBlocked: preview files to import or skip, fix wrong matches with mapping, rerun post-processing, or remap episodes before confirming.

Instructions

Gets a finished download into the library when the *arr never took it: one stuck at importBlocked in get_queue, by its download_id; mapping fixes a wrong match. Previews the files it will import and skip, and never forces one the service refuses. postprocess first reruns NZBGet's post-processing, for a download a broken script left unimportable. remap says which episode an imported file really is. On Grimmory, id is a Bookdrop file from get_queue. Rescan or rename: trigger_scan. An import queues and returns (get_stack_health commands). Previews first; confirm to run. Field reference: arr://docs/import_download.

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": {
      "service": "<service>"
    },
    "name": "import_download"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoFor remap, the Sonarr series: `acquisition.id` on a get_library record. On grimmory, the Bookdrop file to import, from get_queue.
actionNoimport (default): a finished download, by `download_id`. postprocess (NZBGet): reruns its post-processing, by `download_id`. remap (Sonarr): moves imported files to the episodes they really are, with `id` and `reassignments`.import
confirmNoThe token from this tool's preview; pass it back to apply.
dry_runNoPreview only, no token issued: for "what if" questions, not the first step of a change.
libraryNoGrimmory only: the library to import the Bookdrop file into, by name or id. Omit when there is one.
mappingNoWhat each file is. The service judges each mapped file again and imports it only if it accepts it; unmapped files keep its own match.
serviceYes
instanceNoWhich instance (e.g. "4k") when several of this service exist. Omit it when there is one.
download_idNo`downloadId` on the get_queue row (nzbget: or its get_history row).
reassignmentsNoInclude every file the change touches: a file moved onto an episode that already has one must say where that one goes too, or the call is refused.

Output Schema

NameRequiredDescriptionDefault
noopYes
tierYes
toolYes
targetYes
appliedYes
dry_runYes
effectsYes
serviceYes
summaryYes
operationYes
permissionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed13 schema fields changedv2.2.0
    • changedInput schema / properties / confirm / description
      Previous value: -"The token from this tool's preview, passed back verbatim to apply it. Single-use and bound to the previewed arguments."New value: +"The token from this tool's preview; pass it back to apply."
    • changedInput schema / properties / dry_run / description
      Previous value: -"Preview without a confirm token, for \"what would happen if\" questions; not the first step of a real change."New value: +"Preview only, no token issued: for \"what if\" questions, not the first step of a change."
    • changedInput schema / properties / mapping / description
      Previous value: -"What each file really is. The service judges each mapped file again and imports it only if it then accepts it; unmapped files keep its own match."New value: +"What each file is. The service judges each mapped file again and imports it only if it accepts it; unmapped files keep its own match."
    • addedInput schema / properties / mapping / items / properties / album_id
      Added value: +{
      +  "description": "Lidarr: the album, an `albums` id on get_media_details.",
      +  "pattern": "^[1-9]\\d*$",
      +  "type": "string"
      +}
    • removedOutput schema / properties / audit_id
      Removed value: -{
      -  "type": "number"
      -}
    • removedOutput schema / properties / confirm_error
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / confirm_token
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / next_steps
      Removed value: -{
      -  "items": {
      -    "additionalProperties": {},
      -    "properties": {
      -      "arguments": {
      -        "additionalProperties": {},
      -        "properties": {},
      -        "type": "object"
      -      },
      -      "tool": {
      -        "type": "string"
      -      },
      -      "why": {
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "tool",
      -      "arguments",
      -      "why"
      -    ],
      -    "type": "object"
      -  },
      -  "type": "array"
      -}
    • removedOutput schema / properties / permission / properties / reason
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / permission / properties / remedy
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / result
      Removed value: -{}
    • removedOutput schema / properties / unchecked
      Removed value: -{
      -  "items": {
      -    "type": "string"
      -  },
      -  "type": "array"
      -}
    • removedOutput schema / properties / warnings
      Removed value: -{
      -  "items": {
      -    "type": "string"
      -  },
      -  "type": "array"
      -}
  2. Addedv1.84.0

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), it discloses the preview-then-confirm two-phase flow, that the import queues and returns rather than completing (observable via get_stack_health `commands`), that it previews both files imported and skipped, and that it never forces an import the service refuses. That is substantial behavioral context an agent cannot get from structured fields.

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?

Front-loaded and dense with no filler, but the telegraphic style (backticked terms mid-sentence, semicolon-chained clauses) makes it harder to scan than it needs to be. Every sentence carries information, so nothing is wasted.

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 10-parameter, multi-service mutation tool with an output schema present, the description covers the workflow, the preview/confirm contract, service-specific quirks, and the refusal behavior. It even points to a field reference (arr://docs/import_download) for the remainder, so an agent has enough to call it correctly.

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 already 90%, so the schema carries most parameter meaning, but the description adds real value: `mapping` fixes a wrong match, `remap` identifies what an imported file really is, `id` on Grimmory is the Bookdrop file, and `confirm` is the preview token passed back to apply. It stops short of clarifying `instance` or `library` beyond what the schema says.

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?

States a specific verb and resource ('Gets a finished download into the library') plus the precise precondition: a download stuck at `importBlocked` that the *arr never took. It distinguishes itself from sibling tools by naming `get_queue` as the source of the identifier and `trigger_scan` as the tool for rescan/rename instead.

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?

Explicitly routes each variant: `postprocess` for a download a broken script left unimportable, `remap` for deciding which episode an imported file really is, and on Grimmory an `id` from get_queue. It also names the alternative (`trigger_scan`) for the adjacent rescan/rename need, leaving little inference required.

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