Skip to main content
Glama

load_device

Destructive

Search Live's browser for a device and load it onto a track, returning search candidates or the load result.

Instructions

Search Live's browser and load a device onto a track: a search step, then a load step.

Returns:
    Dictionary of search candidates and the selected track on the search step,
    or the load result and the resulting device chain on the load step.

Note:
    A load cannot be aimed inside a rack: measured 2026-09-07 against Live 12.4.5,
    ``rack.view.selected_chain`` read back as written and the device still landed on the
    track. An effect is appended; an instrument replaces the one already there and
    discards it silently, with its settings and the clip envelopes pointing at it: check
    with get_devices first. Loading plug-ins in rapid succession can crash Live
    (measured: a batch load during a plug-in rescan with a licence dialog open took Live
    down), so load one at a time. A load also arms the target track and disarms every
    other one (measured 2026-09-19 against Live 12.4.6: of two armed tracks and an
    unarmed target, the target came back armed and the others disarmed), and nothing
    here reports it. An instrument load renames a track that still has Live's default
    name; an effect never renames.

    Success means the call ran, not that the track sounds: a measured Drum Rack load
    reported success on a silent track, and an empty rack is what that looks like, so
    read ``song.tracks[N].devices[i].chains``, which get_devices does not report. A null
    ``selected_track_same``, ``displaced`` or ``configure_needed`` means the comparison
    failed, not ``false``; the first compares name and track count, not identity.
    ``loaded_device_index`` is the position of the new device, computed only where
    the two chains single out exactly one, and null otherwise.
    ``status: incomplete`` with no candidates means the walk stopped early, not that the
    item is absent: retry ``unreached_roots``; only ``complete`` rules it out. The main
    track has no index: write ``song.view.selected_track`` with ``{"__path__":
    "song.master_track"}`` through lom_set, then load.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
uriNoThe uri of one candidate from a previous search step, copied back verbatim to say which item to load. Resolving it walks the browser a second time, so pass root as well when the item sits deep; item_path avoids the walk altogether and is preferred.
rootNoBrowser category to search inside. Empty searches every category, which is slower and returns more near misses. These are the roots the Remote Script walks; there is no user_folders or legacy_libraries here, although the catalog carries rows for both.
limitNoHow many search candidates to return.
queryNoWhat to look for in the browser, matched against item names, e.g. 'Operator' or 'reverb'. Required for the search step; on the load step it can be dropped once uri or item_path is known.
trackNoTrack to load onto, counted from 0. -1 uses whatever is selected, which is what this did before the argument existed. Naming a track points the selection at it first, so a caller does not have to express the load as two steps and cannot load onto a track that happened to be selected. The selection stays there afterwards and is not put back: the LOM offers nothing to restore it to. 'aimed' reports where it went.
confirmNoFalse searches and loads nothing, reporting the candidates and which track is selected. True loads the item named by uri or item_path.
item_pathNoThe browser item as a LOM path rooted at app, e.g. 'app.browser.instruments.children[3]'. The reliable handle, and the one to prefer: unlike a uri it is not walked for again, so it cannot fail on the walk budget. Every search candidate carries one.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / root / description
      Previous value: -"Browser category to search inside. Empty searches every category, which is slower and returns more near misses."New value: +"Browser category to search inside. Empty searches every category, which is slower and returns more near misses. These are the roots the Remote Script walks; there is no user_folders or legacy_libraries here, although the catalog carries rows for both."
    • changedInput schema / properties / root / enum
      Previous value: -[
      -  "",
      -  "audio_effects",
      -  "clips",
      -  "current_project",
      -  "drums",
      -  "instruments",
      -  "legacy_libraries",
      -  "max_for_live",
      -  "midi_effects",
      -  "packs",
      -  "plugins",
      -  "samples",
      -  "sounds",
      -  "user_folders",
      -  "user_library"
      -]New value: +[
      +  "",
      +  "audio_effects",
      +  "clips",
      +  "current_project",
      +  "drums",
      +  "instruments",
      +  "max_for_live",
      +  "midi_effects",
      +  "packs",
      +  "plugins",
      +  "samples",
      +  "sounds",
      +  "user_library"
      +]
    • addedInput schema / properties / track
      Added value: +{
      +  "default": -1,
      +  "description": "Track to load onto, counted from 0. -1 uses whatever is selected, which is what this did before the argument existed. Naming a track points the selection at it first, so a caller does not have to express the load as two steps and cannot load onto a track that happened to be selected. The selection stays there afterwards and is not put back: the LOM offers nothing to restore it to. 'aimed' reports where it went.",
      +  "minimum": -1,
      +  "title": "Track",
      +  "type": "integer"
      +}
  2. Changed2 schema fields changedv0.1.4
    • changedInput schema / properties / item_path / description
      Previous value: -"The browser item as a LOM path rooted at app, e.g. 'app.browser.instruments.children[3]'. Use this instead of uri when the search could not reach the item within its walk budget."New value: +"The browser item as a LOM path rooted at app, e.g. 'app.browser.instruments.children[3]'. The reliable handle, and the one to prefer: unlike a uri it is not walked for again, so it cannot fail on the walk budget. Every search candidate carries one."
    • changedInput schema / properties / uri / description
      Previous value: -"The uri of one candidate from a previous search step, copied back verbatim to say which item to load."New value: +"The uri of one candidate from a previous search step, copied back verbatim to say which item to load. Resolving it walks the browser a second time, so pass root as well when the item sits deep; item_path avoids the walk altogether and is preferred."
  3. Changed7 schema fields changedv0.1.1
    • addedInput schema / properties / confirm / description
      Added value: +"False searches and loads nothing, reporting the candidates and which track is selected. True loads the item named by uri or item_path."
    • addedInput schema / properties / item_path / description
      Added value: +"The browser item as a LOM path rooted at app, e.g. 'app.browser.instruments.children[3]'. Use this instead of uri when the search could not reach the item within its walk budget."
    • addedInput schema / properties / limit / description
      Added value: +"How many search candidates to return."
    • addedInput schema / properties / query / description
      Added value: +"What to look for in the browser, matched against item names, e.g. 'Operator' or 'reverb'. Required for the search step; on the load step it can be dropped once uri or item_path is known."
    • addedInput schema / properties / root / description
      Added value: +"Browser category to search inside. Empty searches every category, which is slower and returns more near misses."
    • addedInput schema / properties / root / enum
      Added value: +[
      +  "",
      +  "audio_effects",
      +  "clips",
      +  "current_project",
      +  "drums",
      +  "instruments",
      +  "legacy_libraries",
      +  "max_for_live",
      +  "midi_effects",
      +  "packs",
      +  "plugins",
      +  "samples",
      +  "sounds",
      +  "user_folders",
      +  "user_library"
      +]
    • addedInput schema / properties / uri / description
      Added value: +"The uri of one candidate from a previous search step, copied back verbatim to say which item to load."
  4. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only indicate destructiveHint=true and readOnlyHint=false, but the description goes far beyond that: it details side effects like arming/disarming tracks, renaming default tracks, silent replacement of instruments, crash risks with rapid loading, the meaning of success vs. actual sound output, null field semantics, and incomplete status handling. It discloses all known behavioral quirks, providing exceptional transparency.

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?

The description is long but well-structured: it opens with a clear purpose, then covers returns, caveats, and edge cases in a logical order. Every sentence adds value, though it could be slightly tighter. It is not overly verbose for the complexity it conveys, and the front-loaded purpose helps quick scanning.

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?

The description is exceptionally complete for a complex tool. It covers return values, error states, edge cases (null fields, incomplete status), workarounds (master track handling), and even measured behavioral notes against specific Live versions. With an output schema present, the description need not explain every return field, but it goes beyond that to ensure correct invocation and interpretation.

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 baseline is 3. The description does not add significant new parameter semantics beyond what the schema already provides; the schema already explains uri, root, limit, query, track, confirm, and item_path in detail. The description focuses on workflow and behavioral context rather than parameter details, which is acceptable given full schema coverage.

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 description states a specific verb and resource: 'Search Live's browser and load a device onto a track', and clarifies the two-step search-then-load process. It clearly distinguishes itself from siblings like get_devices by explaining it performs a load, not just inspection. The purpose is unambiguous and directly useful.

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?

The description gives explicit guidance: it warns to 'check with get_devices first' before loading instruments (to see what will be discarded), advises loading one at a time to avoid crashes, and explains the search step vs. load step. It doesn't explicitly name alternative tools for different scenarios, but it provides clear context on when and how to use this tool safely.

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