Skip to main content
Glama
Sign In

RoTerminal

by co.roterminal
OverviewDiscussionsAdmin

Your Terminal

track
Destructive

Read and change the person’s Terminal: the grid of live cards they keep, in folders, each read again whenever it’s opened. Actions: list (every folder and card, each card’s id, title, number now and its move; folder: just that one), show (ids, up to 6, or folder: the cards freshly read, each with its rows), make (a folder of live cards, first on Terminal, from a template: game {game: its universe id}; due-diligence {game}; compare {games: [universe ids]}; genre {genre: as Roblox writes it}; word {word}; studio {studio: its key from find}; breaking-out; new-and-growing; hidden-gems; ideas-to-build; roblox-now; or ids: a folder of those cards; or title alone: an empty folder), set (id or folder, set: how it’s shown: view, size, range, rank, filter, games, compare, measure; position: where it goes), refresh (ids; none: every card), rename (id or folder, and title), remove and restore (id or folder; a removed one comes back for a day), move (id or folder, and position: 1 = first), file (ids and folder) and unfile (ids). Opens with RoBot: an account RoBot isn’t open on yet gets not_available.

Input Schema

NameRequiredDescriptionDefault
idNoA card’s id (12 characters, from list or show)
idsNoCards’ ids (show, refresh, make, file, unfile; for move, the order wanted)
setNoFor set: only what changes. view: list, chart, map, table, stat or own; size: small, medium, large, extra large, wide; range: 1D, 1W, 1M, 3M, 1Y or All; rank: players, growth, new, robux or own; filter: all, rising, new or a genre; games: names or ids (["all"] for every one); compare: last period, last year or none; measure: robux, players, visits, daily, new or hours
fillNoFor make: what fills the template, like {game: "grow a garden"}, {games: [..]} or {genre: "Tycoon"}
askedNorename a folder: true only when the person asked for this new name
titleNoA name (rename, make)
actionYes
folderNoA folder’s name or id
positionNoFor move and set: where it goes, 1 = first
templateNoFor make: the folder’s template

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / template / enum
      Previous value: -[
-  "game",
-  "genre",
-  "word",
-  "studio",
-  "breaking-out",
-  "new-and-growing",
-  "ideas-to-build",
-  "roblox-now"
-]New value: +[
+  "game",
+  "due-diligence",
+  "compare",
+  "genre",
+  "word",
+  "studio",
+  "breaking-out",
+  "new-and-growing",
+  "hidden-gems",
+  "ideas-to-build",
+  "roblox-now"
+]
  2. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds useful behavioral context beyond that: removed cards come back 'for a day,' cards are 'read again whenever it’s opened,' and an account without RoBot open gets 'not_available.' It does not fully cover permissions, rate limits, or all mutation side effects, but it does disclose key state and lifecycle behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose, but it is delivered as one very dense run-on paragraph enumerating every action and edge case. The content is mostly necessary for this multi-action tool, yet the lack of bullets or action-by-action structure makes it harder to scan than it should be.

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 complex multi-action tool with 10 parameters, no output schema, and destructive annotations, the description covers all available actions, key parameter pairings, template fill options, restore behavior, and the RoBot availability prerequisite. It remains incomplete on return shapes for many actions and broader error behavior, but it gives an agent enough to select and invoke actions correctly in most cases.

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 high at 90%, so the schema already carries most parameter meaning. The description still adds value by mapping actions to parameters, e.g. show accepts ids or folder with 'up to 6,' refresh with no ids means 'every card,' make uses fill for template-specific values, and rename folders use asked only when the person requested the new name.

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 description states a specific verb and resource: 'Read and change the person’s Terminal,' and explains that the Terminal is a grid of live cards kept in folders. This is clear enough to distinguish it from a generic page or chart tool, though it does not explicitly name sibling tools like page_cards or charts for contrast.

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?

The description gives action-level usage detail, such as 'list (every folder and card...)' and 'show (ids... or folder),' which implies when each action is appropriate. However, it does not state when to use track instead of adjacent tools such as page_cards, charts, or compare, and it offers no explicit exclusions or alternatives.

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

All RoTerminal toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources