Skip to main content
Glama
FullyDefined – AI for SOLIDWORKS

FullyDefined – AI for SOLIDWORKS

add_sketch_relation

Add geometric relations (horizontal, parallel, tangent, symmetric) to open sketch entities by ID, constraining under-defined geometry. User dimensions and relations are protected from conflicts.

Instructions

Add a geometric relation in the open sketch. Entities are given by id (drawing order; see list_sketch_entities): 3 for a whole entity, '3:start', '3:end' or '3:center' for one of its points, or 'origin'. A relation that contradicts a size the tools added from the drawing (named DrawnN) replaces it (the result says which); one that contradicts the user's own dimensions or relations is refused, naming them, and not left in the sketch. Under-defined geometry is free to move, so for 'symmetric' first define the centerline (dimensions or relations) if it must stay put. 'fix' is refused in a part sketch (dimension from the user's references instead) and allowed in an assembly sketch.

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": {
      "relation": "<relation>",
      "entities": "<entities>"
    },
    "name": "add_sketch_relation"
  }
}

Input Schema

NameRequiredDescriptionDefault
unitNoUnit of the 'edge:x,y,z' points (mm, cm, m, inch or ft)
entitiesYesEntity references as strings, e.g. ['1'], ['2', '4'], ['origin', '1:start'], or a model edge by a point on it: ['1:center', 'edge:80,40,5']
relationYesRelation type. horizontal/vertical take one line or two points; merge takes two points; symmetric takes two entities (or two points) plus a centerline.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full disclosure burden and does so well: it says which conflicts silently replace tool-created DrawnN sizes, which are refused with a naming error and left out of the sketch, and that under-defined geometry is free to move. These are exactly the side effects and failure modes an agent needs before calling a mutation tool.

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?

Dense but front-loaded: the core action and the entity-id convention come first, followed by conflict, symmetric, and fix caveats. No sentence is filler, though the lack of any separation makes it harder to scan than it could be.

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

Completeness5/5

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

There is no output schema, and the description only alludes to result content ('the result says which'), but for a 3-parameter sketch-relation call the caller-facing contract is otherwise fully covered. An agent knows the reference format, the relation arity rules, and every refusal case before invoking it.

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 still adds value by explaining that ids follow drawing order, that '3:end' and '3:center' are valid point selectors, and by stating the arity rules for symmetric and the part/assembly restriction on 'fix'. The 'unit' parameter and the edge:x,y,z point form are left mostly to the schema.

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 a geometric relation in the open sketch') and scopes it to the currently open sketch, which cleanly separates it from add_sketch_dimension and fully_define_sketch. The entity-reference syntax that follows immediately confirms exactly what the tool operates on.

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?

Gives concrete situational guidance: call list_sketch_entities for ids, define a centerline before 'symmetric', and use 'fix' only in an assembly sketch. It stops short of explicitly contrasting with sibling tools such as add_sketch_dimension for cases where a dimension is the better choice.

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