Create 2D AutoCAD geometry, annotations, hatches, dimensions, and block references in one atomic action; specify entities, space, and coordinate system.
Atomically create 2D entities, annotations, hatches, dimensions, and block references. Angles are radians and coordinates use the current UCS unless otherwise stated.
| Name | Required | Description | Default |
|---|---|---|---|
| space | No | ||
| entities | Yes | ||
| zoomToResult | No | ||
| coordinateSystem | No |
Changes observed during successful MCP inspections.
v0.0.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnly=false, destructive=false, non-idempotent, closed-world, but the description adds genuine behavioral facts on top: 'Atomically' declares all-or-nothing batch semantics, which is a real transactional guarantee not expressible via the annotations. It also fixes unit/coordinate conventions (radians, current UCS), though it omits the 1000-entity cap and the fact that repeated identical calls will duplicate geometry.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, both front-loaded: the capability first, then the cross-cutting conventions. Every clause carries information and nothing is padding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For an 11-variant polymorphic schema with no parameter documentation and no output schema, the description is thin: it does not mention that a document must be connected first, does not say whether entity handles are returned (which matters because hatch requires boundaryHandles from pre-existing entities), and does not cover the 1000-item batch limit.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% – not a single parameter or sub-field is documented in the schema – so the description carries the full burden. It partially compensates by declaring radians for angular fields and UCS for coordinates (which implicitly explains the coordinateSystem enum), but never explains 'space' (model/paper/current), 'zoomToResult', the entities array shape, or hatch boundaryHandles.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description gives a specific verb (create) plus an enumerated resource set (2D entities, annotations, hatches, dimensions, block references), so an agent can tell this is the drawing/creation tool rather than cad_edit or cad_block. It stops short of naming a sibling to contrast with, so it lands at 4 rather than 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no statement of when to use cad_draw versus cad_command (raw command execution), cad_edit (modify existing), or cad_block (block definition), nor any preconditions such as requiring an open document via cad_connect. The only cue is the word 'create', which is inference rather than guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.