Skip to main content
Glama
FullyDefined – AI for SOLIDWORKS

FullyDefined – AI for SOLIDWORKS

step_mate

Moves an assembly through a list of distance or angle mate values, saves pictures, and counts interferences at each step, returning unfinished values for continuation.

Instructions

Step a distance or angle mate through a list of values, optionally saving a picture (named .png; an existing file is never replaced: the next free name, ' (2).png', is used and reported) and counting interferences at each step: this is how a mechanism is moved and shown. For each value the mate is set, the assembly rebuilt and the mate errors read. The call stops by itself before max_seconds runs out and returns the values still to do, to pass on as first_index; it also stops at the first value the mates do not allow. A PUSHED chain folds if the driven point moves more than one link pitch along its track in one move: set max_change (about half the pitch) and the way between values is walked in smaller moves.

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": {
      "name": "<name>",
      "values": "<values>"
    },
    "name": "step_mate"
  }
}

Input Schema

NameRequiredDescriptionDefault
upNoWith direction: the model direction that points up in the picture
nameYesMate name from list_mates, e.g. 'Distance1'
unitNoUnit of the values for a distance mate (mm, cm, m, inch or ft)
viewNoView for the picturescurrent
widthNoPicture width in pixels (64-4096)
heightNoPicture height in pixels (64-4096)
prefixNoFile name prefix (default: the mate name)
valuesYesValues to step through, in order (distance in unit, or degrees)
directionNoInstead of view: where the camera is, seen from the model
max_changeNoNever change the mate by more than this at once: the way between two values is walked in smaller equal moves, without pictures. Use about half the link pitch for a chain that is pushed.
first_indexNoNumber of the first picture; use it to continue a series
max_secondsNoStop before the call has run this long (5-50)
zoom_to_fitNoZoom to fit once before the first picture (all pictures then have the same scale)
return_imageNoSend the last picture back, or nonelast
output_folderNoFolder on the computer for the pictures. Without it no pictures are saved.
hide_annotationsNoHide dimensions, planes, axes, origins and sketches in the pictures
white_backgroundNoPlain white background
check_interferenceNoCount interferences at every step

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
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 well: it discloses that the call self-terminates before max_seconds and returns remaining values, that it stops at the first disallowed value, that images are never overwritten (next free name is reported), and that pictures require output_folder. It does not say where the mate is left after a partial or failed run, which matters for a mutating 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?

Purpose and the picture/interference behavior are front-loaded, and every clause carries information about behavior an agent must know. The single dense paragraph with nested semicolons and parentheses makes it slightly harder to scan than it needs to be.

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 an 18-parameter, annotation-free mutation tool with no output schema, the description covers the critical behaviors: termination by time or by infeasible values, the returned remaining values, file naming, and the chain-folding workaround. What is missing is the shape of the result beyond the continuation values and the mate's final state.

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, but the description adds real meaning for the parameters that are easy to misuse: max_change ('about half the pitch', smaller equal moves without pictures), first_index (continuation of a series), and output_folder (absent means no pictures). The remaining 14 parameters are left entirely 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?

The description opens with a concrete verb and resource: 'Step a distance or angle mate through a list of values', then extends the scope to picture capture and interference counting. That batch-stepping framing is distinct from single-change siblings like edit_mate, so an agent can tell what this is 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 gives clear operational context ('this is how a mechanism is moved and shown') and specific conditions: use max_change when a PUSHED chain might fold, use returned values as first_index to continue. It stops short of naming an alternative tool such as edit_mate for one-off changes, so there is no explicit when-not guidance.

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