Skip to main content
Glama

Add an object

add_object

Hangs something on a block's side, as near its middle as it fits. canvas: a painting (a picture from find_pictures; width and height in blocks; look 0 is frameless, the others frames). prop: an everyday object (a picture from find_pictures). lamp: width and height 1 or 2. fan: blows away from its side. cannon: on a floor or a wall, for $10 of yours each time (refused, saying so, if you hold fewer); it fires at whoever is near, you included, until its balls run out. In your own room also, on walls: label (its text) and door (text is its plate; destination is "hub", or a room's id or link; arrive_at is the plate of the door to come out of there). On a floor or ceiling, top is the way a picture's top points.

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": {
      "type": "<type>",
      "on": "<on>"
    },
    "name": "add_object"
  }
}

Input Schema

NameRequiredDescriptionDefault
onYesThe block's side it hangs on
topNoOn a floor or ceiling, the way a picture's top points: north (the default), south, east or west. Ignored on a wall.
lookNo
textNo
typeYes
widthNo
heightNo
pictureNo
arrive_atNo
destinationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the bar is lower, but the description adds genuinely useful behavior beyond that: cannon costs $10 per shot and is refused when funds are short, cannon fires at anyone nearby including the caller, fan blows away from its side, and look 0 means frameless. It still omits what happens on other failure modes (occupied side, invalid picture id) and says nothing about the return value, though no output schema exists.

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 structure is front-loaded with the general rule, then a compact 'type: detail' enumeration, so an agent can skim to the relevant clause. The telegraphic phrasing ('for $10 of yours each time (refused, saying so, if you hold fewer)') is dense and occasionally awkward but nearly every fragment carries operational information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter tool with a nested object and no output schema, the description covers most behavioral and per-type semantics, but leaves several parameters (picture, the on-object coordinates) entirely to a schema that is only 20% documented. Error/rejection behavior is described for cannon only, so completeness is good but uneven.

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?

With schema description coverage at only 20%, the description carries the load well: it explains type-specific meaning for width/height (canvas in blocks; lamp 1 or 2), look (0 frameless, others framed), text (label text, door plate), destination ('hub', a room id or link), arrive_at (plate of the door you exit), and top (picture orientation on floors/ceilings, ignored on walls). Gaps remain: the picture parameter is only implied by 'a picture from find_pictures', and the nested 'on' object's row/column/layer/side are left to the schema.

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 first sentence gives a specific verb and resource (hanging an object on a block's side, centered as far as it fits), and the per-type clauses (canvas, prop, lamp, fan, cannon, label, door) make the scope concrete. It does not explicitly distinguish itself from siblings like edit_object, move_object, or remove_object, so an agent must infer the create-vs-modify boundary.

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 rather than stated: pictures for canvas/prop come from find_pictures, cannon requires enough money, and label/door only apply in your own room on walls. There is no explicit 'use this instead of X' routing against the many sibling mutation tools, and no statement of prerequisites such as room ownership beyond the parenthetical.

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.