Skip to main content
Glama

fx

Add, remove, bypass, or move plugins in a REAPER track's effect chain using fuzzy name matching, with dry-run preview.

Instructions

FX chain operations: add (fuzzy plugin-name resolution against REAPER's installed-plugin cache), remove, bypass, move. Undo-block wrapped; supports dry_run (dry_run add needs the exact fx_name, no fuzzy resolution). TO ADD A PLUGIN, JUST RUN add IN ONE CALL. The resolver against the installed-plugin cache IS the check — a plugin being absent from the project is normal and expected (adding it is the whole point). Do NOT precheck with scan_fx, do NOT hedge about whether it's installed, do NOT narrate a plan. Target the master with track:"master". The user may be recording live; extra steps and preamble ruin the take. To change a parameter on an FX already in the chain use set_fx_param.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
showNoadd: open the FX window.
trackNoExact track name (case-insensitive); "master" targets the master track. Used when no GUID is given; errors if two tracks share the name.
actionYes
bypassNo
dry_runNoPreview: return what would run without changing the project.
fx_nameNoadd: plugin name or fuzzy query (e.g. 'pro q 4').
fx_indexNo
fx_scopeNoRequired with fx_index.
to_indexNo
track_containsNoCase-insensitive substring; used only when no GUID or exact name is given. Errors if it matches more than one track.
fx_name_containsNoremove/bypass/move: substring selector.
target_track_guidNoStable REAPER track GUID; preferred when available. Wins over every other track selector.
use_selected_trackNoTarget the first selected track; ignored when any other track selector is given. Errors if nothing is selected.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv3.21.0
    • changedInput schema / properties / target_track_guid / description
      Previous value: -"Stable REAPER track GUID; preferred when available."New value: +"Stable REAPER track GUID; preferred when available. Wins over every other track selector."
    • changedInput schema / properties / track / description
      Previous value: -"Exact track name (case-insensitive)."New value: +"Exact track name (case-insensitive); \"master\" targets the master track. Used when no GUID is given; errors if two tracks share the name."
    • changedInput schema / properties / track_contains / description
      Previous value: -"Case-insensitive substring; errors if it matches more than one track."New value: +"Case-insensitive substring; used only when no GUID or exact name is given. Errors if it matches more than one track."
    • changedInput schema / properties / use_selected_track / description
      Previous value: -"Target the currently selected track instead of naming one."New value: +"Target the first selected track; ignored when any other track selector is given. Errors if nothing is selected."
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full disclosure burden and does so thoroughly: it states undo-block wrapping, dry_run behavior, the exact dry_run add exception, and the installed-plugin-cache-as-validation model. This prevents an agent from incorrectly treating an absent plugin as an error, which is a non-obvious behavioral trait.

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 longer than average, but nearly every sentence carries operational weight, especially the warnings about scan_fx and live recording. The repeated negative directives ('do NOT precheck... do NOT hedge... do NOT narrate') are emphatic rather than informational, so it is not perfectly concise, but it is front-loaded and well-organized.

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 13-parameter tool with no output schema, the description covers the critical add workflow, dry_run exception, track targeting, and sibling routing. It leaves some context unspecified, such as what a successful call returns and the detailed selection semantics for move/bypass, but these are either inferable from the schema or less critical to a first correct call.

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?

Beyond the 69% schema coverage, the description adds meaningful semantics for key parameters: fx_name is a fuzzy query, dry_run add requires an exact fx_name with no fuzzy resolution, and track accepts 'master' as a special target. It does not narrate per-action parameter combinations for remove/bypass/move, but the schema largely covers those selectors.

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 line states the exact resource ('FX chain operations') and enumerates the four distinct verbs: add, remove, bypass, move. It further narrows 'add' semantics with fuzzy plugin-name resolution, making the tool distinguishable from siblings like set_fx_param and scan_fx without inspecting 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?

The description gives explicit routing: 'To change a parameter on an FX already in the chain use set_fx_param' and 'Do NOT precheck with scan_fx.' It also prescribes the exact call pattern for adding ('JUST RUN add IN ONE CALL') and for targeting the master track ('track:"master"').

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