Skip to main content
Glama
FullyDefined – AI for SOLIDWORKS

FullyDefined – AI for SOLIDWORKS

list_sketch_entities

Lists open sketch entity IDs, coordinates, sizes, dimensions, relations, and definition status so you can target correct IDs for adding relations or dimensions and verify closed contours.

Instructions

List the open sketch's entities (ids, coordinates, sizes), dimensions, relation count and definition status (under_defined / fully_defined / over_defined). The ids are what add_sketch_relation and add_sketch_dimension take. They follow drawing order (1 = the first entity drawn; a rectangle is 4 entities) and stay the same when more geometry is added. Every line, arc and spline also gets start_joins / end_joins: the ends of other entities at the same place, as 'id:start' / 'id:end'. open_ends lists the ends that touch nothing (construction geometry does not count), so an empty open_ends means every contour is closed.

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": "list_sketch_entities"
  }
}

Input Schema

NameRequiredDescriptionDefault
unitNomm, cm, m, inch or ft

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
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 does most of it: it discloses id ordering and stability, the start_joins/end_joins string format, and the non-obvious rule that construction geometry does not count toward open_ends. What it omits is failure behavior — e.g. what happens when no sketch is open or when the sketch is not in edit mode — and it never explicitly states the call is a read-only/no-mutation operation.

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 purpose, then progressively deeper semantics about ids, joins, and open_ends; no sentence is filler or a restatement of the name. It is a single dense block rather than being broken into labeled parts, which makes the joins/open_ends rules slightly harder to scan but costs nothing in precision.

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?

No output schema and no annotations exist, so the description has to explain return values — and it does so thoroughly, down to the 'id:start'/'id:end' join encoding and the meaning of an empty open_ends. What remains uncovered is precondition/error context (no open sketch, sketch not in edit mode) and any hint about result volume for complex sketches.

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

Parameters5/5

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

Only one optional parameter ('unit') and the schema documents it at 100% coverage with its allowed values, so the schema already does the work. The description adds the relevant semantic link by naming 'coordinates' and 'sizes' as returned values, implying units apply to reported geometry, without needing to restate the enum.

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 ('List the open sketch's entities'), enumerates exactly what is returned (ids, coordinates, sizes, dimensions, relation count, definition status), and ties the output to sibling tools ('The ids are what add_sketch_relation and add_sketch_dimension take'). An agent can distinguish this from the add_*/fully_define_sketch family without opening a 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?

Guidance is clear for the primary downstream use: fetch ids here before calling add_sketch_relation or add_sketch_dimension. It also explains why ids remain stable when geometry is added, which justifies re-listing habits. It stops short of explicit exclusions, notably failing to differentiate from the sibling get_sketch_status even though this tool also reports definition status.

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