Skip to main content
Glama

chamfer_execute

Execute ordered 2D CAD drafting commands in millimeters atomically, then run geometry and manufacturing verification to confirm the design is buildable.

Instructions

Execute deterministic 2D CAD drafting commands in millimeters atomically and run manufacturing/geometry verification. Supported commands: NEW [name], LAYER [#hex] [CONSTRUCTION], RECTANG <x1,y1> <x2,y2> [id=...], PLINE [... C] [id=...], LINE [...] [id=...], CIRCLE <cx,cy> [D] <r_or_d> [id=...], ARC [id=...] (or ARC C <cx,cy> <start_deg> <end_deg>), OFFSET [entity_id] <side_x,y> [id=...], CHAMFER, FILLET, TRIM, ROTATE, MIRROR, ARRAY, TEXT, DIM <dim_pt> [id=...], SELECT <ALL|NONE|ids>, MOVE , COPY , ERASE [ids], UNDO, REDO.

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": {
      "commands": "<commands>"
    },
    "name": "chamfer_execute"
  }
}

Input Schema

NameRequiredDescriptionDefault
commandsYesOrdered CAD commands to execute atomically.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose key traits: units are millimeters, execution is deterministic, and the batch is atomic (all-or-nothing). It also mentions running manufacturing/geometry verification, though it never says whether verification is automatic or a side effect, nor what happens on a failing command mid-batch.

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 lead sentence is well front-loaded, but the command catalog is a single dense run-on with no line breaks or grouping, and it is internally inconsistent: RECTANG, PLINE, ARC, and OFFSET get full syntax while CHAMFER, FILLET, TRIM, ROTATE, MIRROR, ARRAY, and TEXT are bare keywords. Some of the enumeration earns its place, but the inconsistent treatment wastes space without delivering usable syntax.

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 single-parameter DSL executor with no output schema, the grammar is the critical missing piece, and roughly a third of the listed commands have no documented arguments at all. Return values, error/rollback reporting, and the meaning of the verification step are also unaddressed, leaving real gaps for an agent composing a command batch.

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 says 'ordered CAD commands' as an array of strings; the description supplies the entire DSL grammar, argument order, optional id= naming, and unit conventions that an agent cannot infer from the schema. This is exactly the kind of meaning the schema cannot carry, so it exceeds the 100%-coverage baseline of 3.

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 names a specific verb ('Execute') and resource ('deterministic 2D CAD drafting commands in millimeters'), and the command list makes the tool's scope unmistakable. It implicitly separates this drafting/execution engine from siblings like chamfer_export_dxf or chamfer_lint, but never explicitly states the boundary, so it stops 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 only implied: the command list tells an agent what kinds of tasks belong here (drawing creation, layer setup, geometry edits), and 'atomically' hints at batching multiple steps. There is no explicit when-to-use/when-not guidance and no routing to chamfer_modify_entity, chamfer_lint, or chamfer_get_drawing for single-entity edits or validation.

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