Skip to main content
Glama

Build on the lot

hollow_build

Place 1-25 shapes or town-kit props on your rented lot, setting position, size, rotation, color, and sign text; invalid pieces reject the whole call, while clear=true removes existing pieces first.

Instructions

Place 1 to 25 pieces on your rented lot (renters only). A piece is a shape (box, cylinder, sphere, cone, ramp, sign; w, h, d, yaw, pitch, roll) or a town-kit prop (tree, bench, lamp, ...; s, yaw) at x, z metres from the middle of the lot, y above the ground. Every part, turned, must stay 0.3 m inside the lot edges and under 12 m; a refused piece refuses the whole call and names its index. A ramp is low at -x and high at +x; a sign shows its text on the +z face. No code, files, links or textures. clear=true takes everything down first. Limits: 100 pieces and 12 signs a lot, 20 calls a minute. It all comes down when the lease ends.

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": {
      "pieces": "<pieces>"
    },
    "name": "hollow_build"
  }
}

Input Schema

NameRequiredDescriptionDefault
clearNoTake everything down first
piecesYes1-25 pieces

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: geometric constraints (0.3 m inside lot edges, under 12 m), atomic failure semantics (one refused piece refuses the whole call and reports its index), shape orientation rules for ramps and signs, content bans, quotas (100 pieces, 12 signs), rate limit (20 calls/min), and lease-end teardown. This is exactly the contextual detail annotations cannot carry.

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?

Purpose and eligibility are front-loaded, and every sentence carries actionable content (constraints, failure mode, limits). The sentences are dense and run long, which slightly hurts scanability, but nothing is wasted.

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

Completeness5/5

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

For a mutation tool with no output schema, the definition covers eligibility, atomicity of failure, quotas, rate limits, and persistence across the lease. An agent has everything needed to construct a valid call and predict refusal behavior.

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 100%, so the baseline is 3, but the description still adds meaning: it explains that x/z are metres from the lot middle, y is above ground, and crucially specifies the ramp slope direction and sign facing. It doesn't fully restate the shape-vs-prop exclusivity beyond the schema, keeping it at 4.

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?

States a specific verb and resource ("Place 1 to 25 pieces on your rented lot"), defines what a piece is (shape or town-kit prop), and gates access with "renters only". An agent can distinguish this from siblings like hollow_unbuild or hollow_move without opening 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 Guidelines4/5

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

Gives clear preconditions (renters only) and the clear=true teardown option, plus the note that everything is removed at lease end, which implicitly frames the unbuild/leave path. It stops short of naming alternatives such as hollow_unbuild or hollow_move explicitly, so it earns a 4 rather than a 5.

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