Skip to main content
Glama

Change authored plugins

AccountAuthoringWriteTool
Destructive

Create or update a third-party plugin the account is building, and hide or unhide a failing install of a published plugin.

  • createMyPlugin: Start a third-party plugin — params: name (body), description (body: at most 35 characters), category (body: One or more of the categories listCategories answers), refresh_every (body: one of 1440, 720, 480, 360, 240, 120, 60, 30, 15), no_screen_padding (body), installation_url (body: Where an installer is sent to connect; your OAuth authorize page), plugin_management_url (body: Where an installer manages the connection on your site), plugin_markup_url (body: Your endpoint that answers the markup for a render), installation_success_webhook_url (body), uninstallation_webhook_url (body), knowledge_base_url (body)

  • updateMyPlugin: Change a third-party plugin — params: id (path), name (body), description (body: at most 35 characters), category (body: One or more of the categories listCategories answers), refresh_every (body: one of 1440, 720, 480, 360, 240, 120, 60, 30, 15), no_screen_padding (body), installation_url (body: Where an installer is sent to connect; your OAuth authorize page), plugin_management_url (body: Where an installer manages the connection on your site), plugin_markup_url (body: Your endpoint that answers the markup for a render), installation_success_webhook_url (body), uninstallation_webhook_url (body), knowledge_base_url (body)

  • hideAuthorPluginError: Hide an error row from your analytics — params: kind (body: one of recipe, third_party), subject_id (body: The recipe or third-party plugin id of the row), owner (body: one of author, upstream, installer_connection, installer_setup), message (body: The row message; it is matched by shape, so numbers and urls in it may differ)

  • unhideAuthorPluginError: Show a hidden error row again — params: kind (query: one of recipe, third_party), subject_id (query), owner (query: one of author, upstream, installer_connection, installer_setup), message (query)

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": "AccountAuthoringWriteTool"
  }
}

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

A4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=false, openWorldHint=false, so the safety profile is carried structurally. The description adds real behavioral detail beyond that: hide is reversible via unhideAuthorPluginError, hidden rows can be restored, and the message match is by shape so numbers and URLs may differ. It stops short of saying whether updateMyPlugin replaces or merges existing fields, which for a destructive non-idempotent write is the notable remaining gap.

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 with a one-sentence summary, then scannable per-action bullets, so an agent can jump straight to the action it needs. The cost is that updateMyPlugin repeats all twelve createMyPlugin parameters virtually verbatim, roughly doubling the volume of the densest section; that redundancy is the only structural weakness.

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 four-operation mutation tool with a nested params object and no output schema, the description covers operation semantics and parameters thoroughly, so an agent can construct a call correctly. It is thin on update semantics (partial vs full replacement) and on the authorization or scope requirements for authoring plugins, and with no output schema there is no statement of what a successful call returns.

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

Parameters5/5

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

The schema only exposes an action enum and an untyped params bag, so the description is the sole source of operation-level parameter meaning, and it delivers: per-action param lists, body vs path vs query placement, the 35-character description cap, the explicit refresh_every value set, and plain-language glosses for installation_url, plugin_management_url and plugin_markup_url. Hide/unhide correctly document body vs query placement differences.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence gives a specific verb set and resource: create/update an authored third-party plugin, and hide/unhide a failing install error row. Each of the four actions is then named and scoped, so an agent can tell this apart from AccountPluginSettingsWriteTool or AccountPluginsTool by the 'authored/third-party plugin the account is building' framing. It never explicitly contrasts with those siblings, which keeps it at 4.

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 action names and by hints such as 'category (body: One or more of the categories listCategories answers)', which routes the agent to another tool for enum values. But there is no explicit guidance on when to use createMyPlugin vs updateMyPlugin for an existing plugin, on what to do when an install is failing, or on when to reach for AccountPluginsTool/AccountPluginSettingsWriteTool instead. Context is present; conditional selection rules are not.

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