Skip to main content
Glama
kompas-mcp

kompas-mcp

by biryak

Fillet / chamfer

part_fillet_chamfer

Apply fillets or chamfers to geometry-selected edges; verify the result, restore on failure, and return handles, volume/mass changes, and a backup path.

Instructions

Fillet or chamfer on edges chosen by geometry (never by index). Returns a receipt: created object handles, volume/mass before and after, backup path. The whole call is ONE Ctrl+Z for the user; if verification fails the model is restored and VERIFY_FAILED is returned.

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>",
      "kind": "<kind>",
      "edges": "<edges>",
      "size": "<size>"
    },
    "name": "part_fillet_chamfer"
  }
}

Input Schema

NameRequiredDescriptionDefault
docYesDocument handle from doc_list/doc_open, e.g. 'doc:12001:0a1b2c3d'
kindYes
nameNoMeaningful feature name for the tree, e.g. 'Отв_крепёжные_6xD11'
sizeYesfillet radius / chamfer leg, mm
angleNochamfer angle, degrees
edgesYestopo: edges from select(kind='edge', expect_count=...)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.2

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare the safety profile (not read-only, not idempotent, not destructive), and the description adds substantial context beyond that: the returned receipt contents (handles, volume/mass before and after, backup path), atomic undo semantics ('ONE Ctrl+Z'), and the failure path where the model is restored and VERIFY_FAILED is returned. That is exactly the kind of mutation-risk and rollback disclosure an agent needs before calling a geometry-editing tool.

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 sentences, front-loaded with the operation and selection rule, then the receipt and rollback guarantees. No filler, no restatement of the title, and each clause carries information an agent would otherwise have to guess.

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 non-idempotent geometry mutation with no output schema, the description covers the essential gaps: what is returned, that the operation is atomic and undoable, and how failure manifests. Minor omissions remain — whether angle is ignored for fillets, and any permission or document-state requirements — but nothing critical is missing for a correct call.

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

Parameters4/5

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

Schema coverage is 83%, so most parameters are already documented (doc handle format, size as radius/leg, angle bounds, edges sourced from select). The description still adds meaning the schema does not state — that edge identity must be geometric, never positional — which changes how the edges array must be populated. The remaining parameters (name, angle applicability per kind) get no extra clarification.

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?

The description names a specific modeling operation (fillet or chamfer) applied to a defined resource (edges selected by geometry), and the constraint 'never by index' immediately separates it from any index-based edge workflow. Together with the name and the part_* sibling family, an agent can tell exactly what this tool does 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?

It states a real precondition: edges must be chosen by geometry and supplied from select(kind='edge', expect_count=...) rather than by index, which tells the agent which upstream tool to call first. It does not say when to prefer a fillet over a chamfer beyond the kind enum, nor when to avoid this tool entirely (e.g. on faces or vertices), so it stops short of full routing guidance.

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