Skip to main content
Glama
FullyDefined – AI for SOLIDWORKS

FullyDefined – AI for SOLIDWORKS

select_edges

Select body edges by points, face points, or edge IDs, then filter by type, axis, or loop to prepare accurate fillets and chamfers in SOLIDWORKS.

Instructions

Select body edges by geometry (the view does not matter), ready for fillet_edges / chamfer_edges. Choose by points (the edge nearest each point), face_points (one point = every edge bordering that face; two points = the edge the two faces share) or edge_ids from list_edges (refused if the geometry changed since it listed them; points are safer). With none of these, a filter alone selects from all edges. The filters edge_type, parallel_to and loop narrow the choice.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "select_edges"
  }
}

Input Schema

NameRequiredDescriptionDefault
loopNoWith one face point: the face outline (outer), its hole edges (inner) or bothall
unitNomm, cm, m, inch or ft
appendNoAdd to the current selection instead of replacing it
pointsNoModel points on or near the edges to select (one edge per point)
edge_idsNoEdge ids from list_edges
edge_typeNoKeep only edges of this type
toleranceNoHow far a point may be from its edge (default 0.5 mm)
face_pointsNoOne point inside a face = all its edges; two points on two faces = their shared edge
parallel_toNoKeep only straight edges parallel to this model axis

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
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 it delivers real behavioral facts: view-independence, the stale-id refusal for edge_ids, the relative safety of points, and how filters combine with the modes. It stops short of saying what happens when nothing matches, whether the selection persists, or what the call reports back.

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?

Front-loaded with the purpose, then mode-by-mode, then filters — a logical order with no filler sentences. It is dense to the point of run-on in the nested parentheticals, which costs a little readability but wastes no content.

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 9-parameter, zero-annotation, no-output-schema selector, the description covers the decision logic an agent actually needs and defers the rest to a fully documented schema. The remaining gap is outcome behavior — empty matches, error signaling, and selection persistence — which nothing else supplies.

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 100%, so the baseline is 3; the description earns above that by explaining that edge_ids come from list_edges and can be rejected after geometry changes, and by stating the filter-only fallback that the schema does not imply. It leaves unit, append, and tolerance entirely to the schema, which is acceptable given full coverage.

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 ('Select body edges by geometry') and immediately names the downstream siblings it feeds (fillet_edges / chamfer_edges), which cleanly separates it from list_edges and select_faces. The parenthetical 'the view does not matter' preempts a plausible confusion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly enumerates the three selection strategies (points, face_points, edge_ids) with the condition that picks each, and adds a fourth mode ('with none of these, a filter alone selects from all edges'). It also gives a preference rule: edge_ids are refused if geometry changed, and 'points are safer'.

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

Deploy Server

Other Tools