Skip to main content
Glama
kompas-mcp

kompas-mcp

by biryak

Add section

drw_add_section

Creates a section (разрез) or cross-section view from a cutting line on an associative base view, keeping the base scale. Use it to cut A-A and place the resulting view freely or in projection link.

Instructions

Cutting line A-A on an associative view and the section view (разрез) or cross-section (сечение) built from it, in the base view's scale; one Ctrl+Z. Check the result with view_capture.

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>",
      "base_view": "<base_view>",
      "line": "<line>"
    },
    "name": "drw_add_section"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNosheet position of the new view, mm. Give BOTH x and y for free placement; with one or none the view stays in projection link with its base (aligned along the cut direction)
yNosheet position of the new view, mm
docYesDocument handle from doc_list/doc_open, e.g. 'doc:12001:0a1b2c3d'
kindNosection = разрез, cut = сечениеsection
lineYes[x1, y1, x2, y2] cutting line in the base view, model mm from the model origin (e.g. through the axis of a flange on its front view: [-80, 0, 80, 0])
letterNodesignation letter (ГОСТ 2.305: А, Б, В …)А
base_viewYesnumber of an associative view (from drw_create_views)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare a non-read-only, non-destructive, non-idempotent operation. The description adds genuinely new behavioral facts beyond that: the new view inherits the base view's scale, and the whole operation is undone with a single Ctrl+Z, which tells the agent the mutation is cheaply reversible. It omits failure modes (e.g. a cutting line that misses the geometry), but the added context is solid given annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the object being created and ending with the concrete verification step. Nothing is redundant, and the terse ellipsis is a defensible trade for compactness.

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

Completeness4/5

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

For a 7-parameter drafting mutation with no output schema, the description covers what is produced, the scale semantics, undoability, and a way to confirm the result. Only the failure conditions and what the tool returns on success remain unspecified, which is a minor gap.

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 100%, so coordinates, kind, letter and projection-link behavior are already documented in the schema itself. The description reinforces that the line is a cutting line designated A-A, but adds no syntax or format details beyond the schema's own example, so the baseline of 3 applies.

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 names the concrete artifact produced: the cutting line A-A on an associative view plus the resulting section (разрез) or cross-section (сечение), drawn at the base view's scale. The verb is elided (it reads as a noun phrase), but the resource and effect are specific enough to distinguish it from siblings like drw_create_views or drw_view_edit.

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: base_view is 'from drw_create_views', so an agent infers this is a follow-up step after view creation, and 'Check the result with view_capture' gives a post-call verification path. There is no explicit when-to-use vs when-not guidance, and no stated alternative for editing an existing section (e.g. drw_view_edit).

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