Skip to main content
Glama
kompas-mcp

kompas-mcp

by biryak

Create drawing views

drw_create_views

Adds associative standard views with centerlines to a KOMPAS-3D drawing from a saved model, so projections follow model changes. Position views, set scale, then add sections and dimensions.

Instructions

Add standard ASSOCIATIVE views of a saved model to a drawing (they follow model changes), with centre lines. Check the layout with view_capture. Sections: drw_add_section. Dimensions: drw_add_dimension.

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": {
      "doc": "<doc>",
      "model_path": "<model_path>"
    },
    "name": "drw_create_views"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNofront view position on the sheet, mm
yNofront view position on the sheet, mm
docYesDocument handle from doc_list/doc_open, e.g. 'doc:12001:0a1b2c3d'
gapNodistance between views, mm
scaleNoГОСТ 2.302: 1, 0.5, 0.4, 0.25, 2, 2.5, 4 …
viewsNostandard projections (ЕСКД layout: top below, left to the right of the front view)
model_pathYessaved .m3d/.a3d inside the allowed roots
centerlinesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.0

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already disclose the mutation shape (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false). The description adds genuine value with the associativity contract ('they follow model changes') and the centerlines behavior, which no annotation conveys. It still omits what happens to pre-existing views on the sheet and whether the drawing must be the active document.

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?

One front-loaded sentence carrying the core behavior, followed by short routing fragments; no filler. The telegraphic 'Sections: ... Dimensions: ...' style is efficient but slightly clipped, and the parenthetical costs a beat before the key point.

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?

With 8 parameters at 88% coverage, annotations present and no output schema, the description covers purpose and next steps. It leaves open what the tool returns (view handles/identifiers) and whether existing views are replaced or added alongside, which matters for a non-idempotent mutation on a drawing sheet.

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

Parameters3/5

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

Schema description coverage is 88%, so placement (x/y), gap, scale, view list and the doc handle are already documented in the schema, including ГОСТ 2.302 and ЕСКД notes. The description only echoes the centerlines behavior and does not clarify units, defaults or the interaction between scale and view positions beyond what the schema says. Baseline 3 applies.

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 ('Add standard ASSOCIATIVE views of a saved model to a drawing') plus a distinguishing behavioral property (views follow model changes) and the centreline side effect. An agent can distinguish this from view-creation-adjacent siblings 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?

Explicitly routes follow-up work: 'Check the layout with view_capture', sections go to drw_add_section, dimensions to drw_add_dimension. It gives clear context and alternatives for post-creation steps, but does not state when to prefer this over a view-editing sibling (e.g. drw_view_edit) or any prerequisites such as the drawing needing to be open.

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