Skip to main content
Glama

sharp_world_assembly_and_optimization

Destructive

Audit and repair overlapping or floating anchored top-level Roblox assets, preserving locked objects and reporting unresolved issues for static or gate audits.

Instructions

Audit or iteratively fix OBB overlaps and floating anchored top-level assets.

Floating checks ignore models containing unanchored parts and assets with SharpAllowFloating=true. Repairs never move SharpLocked assets. Grounding requires a raycast hit; voids remain unresolved. float_tolerance_studs is clamped to 0..512 and max_iterations to 1..64. Pass the returned result as world_stats to sharp_critical_audit(mode="static" or "gate"): overlapCount/floatingCount reflect the final re-audit, also available as remainingOverlapCount/remainingFloatingCount after repairs. allClean is false when locked assets, voids, or iteration limits prevent repair. fixedCount counts movement operations, including grounding.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "sharp_world_assembly_and_optimization"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNo
actionNoinstall
max_xzNo
min_xzNo
max_countNo
studio_idNo
root_prefixNo
max_iterationsNo
tolerance_studsNo
execute_in_studioNo
expected_place_idNo
min_spacing_studsNo
float_tolerance_studsNo
expected_session_nonceNo
invoke_upstream_studiomcp_if_plugin_offlineNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.6/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, yet the description adds substantial context beyond them: floating checks skip unanchored models and SharpAllowFloating=true assets, repairs never move SharpLocked assets, grounding needs a raycast hit, and voids stay unresolved. It also defines allClean and fixedCount semantics, which is exactly the kind of edge-case disclosure a destructive tool needs.

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 description is front-loaded with the core action and then layers constraints and return-value semantics in short, dense sentences. Nothing is obviously redundant, though the telegraphic style (fragments like 'Grounding requires a raycast hit; voids remain unresolved.') trades readability for brevity.

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 15-parameter, destructive, no-output-schema tool, the behavioral coverage is strong but the parameter coverage is thin, and there is no explanation of what the returned object contains beyond the named count fields. An agent could invoke it correctly in spirit but would be guessing on most arguments.

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

Parameters2/5

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

Schema description coverage is 0% across 15 parameters, so the description carries the full burden and largely fails to. It documents only float_tolerance_studs (clamped 0..512) and max_iterations (1..64), leaving seed, action, min/max_xz, max_count, root_prefix, tolerance_studs, min_spacing_studs, execute_in_studio, and the expected_* guard parameters entirely unexplained.

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 opens with a specific verb pair and resource: 'Audit or iteratively fix OBB overlaps and floating anchored top-level assets.' That is far more precise than the tool name suggests, and it implicitly separates the audit half from the repair half. It does not explicitly name a sibling it is not, so it falls short of a 5.

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: the reader learns the result should be passed to sharp_critical_audit(mode="static" or "gate"), which hints at a workflow position, but there is no explicit 'use this when X, use Y instead' guidance. The conditions under which repair is impossible (locked assets, voids, iteration limits) are described, which helps an agent decide whether to retry.

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