Skip to main content
Glama

Change plugin settings

AccountPluginSettingsWriteTool
Destructive

Create, rename, configure, copy or delete plugin instances (plugin settings): push data or an image, replace a private plugin's files, reset health or state, and manage the featured image and transform. deletePluginSetting and resetPluginSettingCredentials are destructive.

  • createPluginSetting: Create a new plugin setting — params: name (body), plugin_id (body), plugin_keyname (body: A native plugin's keyname, sent in place of plugin_id)

  • updatePluginSetting: Rename a plugin setting or change how it refreshes — params: id (path), name (body), description (body), refresh_interval (body: one of 1440, 720, 480, 360, 240, 120, 60, 30, 15, 10, 5), health_notification_enabled (body: Email the owner when the instance starts failing), stopped_notification_enabled (body: Email the owner when the instance stops refreshing)

  • deletePluginSetting: Delete a plugin setting — params: id (path)

  • updatePluginSettingFields: Update plugin settings fields — params: plugin_setting_id (path), fields (body)

  • updatePluginSettingData: Update data for a webhook plugin setting — params: id (path), merge_variables (body)

  • importPluginSettingFiles: Replace the files of a private plugin — params: plugin_setting_id (path), files (body)

  • uploadPluginSettingImage: Upload an image for a webhook_image plugin — params: id (path), image_base64 (body: The image bytes, base64 encoded)

  • copyPluginSetting: Copy a plugin setting — params: id (path)

  • clearPluginSettingState: Clear the state a plugin setting has accumulated — params: id (path)

  • enablePluginSettingDebugLogs: Turn on debug logs for a day — params: id (path)

  • resetPluginSettingHealth: Reset the health of a plugin setting that stopped rendering — params: id (path), include_forks (query)

  • setPluginSettingFeaturedImage: Generate the marketplace preview image of a plugin setting — params: id (path)

  • removePluginSettingFeaturedImage: Remove the marketplace preview image of a plugin setting — params: id (path)

  • removePluginSettingTransform: Remove the transform script of a private plugin — params: id (path)

  • verifyCustomFields: Check the custom fields YAML of a recipe — params: custom_fields (body: The custom fields as a YAML list)

  • resetPluginSettingCredentials: Forget the linked account and remove the plugin setting — params: id (path)

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": "AccountPluginSettingsWriteTool"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesThe API operation to run
paramsNoThe operation's path, query and body parameters by name

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true for the whole tool, and the description adds rare sub-action granularity by naming deletePluginSetting and resetPluginSettingCredentials as the destructive ones — refining rather than repeating the annotation. It also discloses side effects an agent could not otherwise predict: emails sent to the owner on failure/stop, debug logs lasting a day, forgetting the linked account on credential reset, and generating a marketplace preview image. It stops short of saying whether deletions are reversible or require confirmation.

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 summary sentence followed by a scannable action/param list — an efficient structure for a 16-operation tool. A few lines spend words without adding information, notably 'deletePluginSetting: Delete a plugin setting — params: id (path)' and 'copyPluginSetting', which restate the action name rather than explain behavior.

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 tool with 16 multiplexed operations, no output schema, and nested params, the definition is nearly sufficient: every action is present, parameter placement is documented, and the destructive subset is flagged. The remaining gaps are the undefined shapes of 'fields' and 'merge_variables' and the absence of any note on return values or on what a copy produces.

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?

Top-level schema coverage is 100% but only describes the generic action enum and an opaque 'params' object, so the description carries the real per-action parameter burden and does it well — path vs body vs query placement, the allowed refresh_interval values (1440 through 5), and the base64 encoding and webhook_image plugin constraint for image upload. Some actions remain thin: updatePluginSettingFields only says 'fields (body)' and updatePluginSettingData only 'merge_variables (body)', with no shape or meaning.

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 (plugin settings) and enumerates the concrete operations — create, rename, configure, copy, delete, push data/image, replace files, reset health/state, featured image, transform. The 16 action entries map one-to-one onto the action enum, so an agent knows exactly what surface this tool covers and can distinguish it from the AccountPluginSettingsReadTool sibling.

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

Usage Guidelines3/5

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

Usage is implied by the Write/Read tool split and by per-action hints such as 'reset the health of a plugin setting that stopped rendering' and 'A native plugin's keyname, sent in place of plugin_id'. However, it never explicitly states when to use this tool versus the read sibling, nor does it warn that exactly one action must be chosen per call. Guidance is inferable but not stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources