Xem Studio: Part Dimensions & CAD

Identify an object from measured sizes

find_by_dimensions

Read-onlyIdempotent

Identify what an object is from one to four sizes you measured (an outline, a bore, a pin, a flange) when you do not know its name; use find_geometry when you do. Each size is compared, within tolerance_mm, against every object's overall size in any order and against its exact feature sizes (bores, slots, pins, size-table rows). Results are ranked with all overall sizes matching first, then by the number of matching features, and each says which of your numbers matched where. No match is not an error: widen tolerance_mm (0.2 suits caliper readings of machined parts, 1 suits rough measurements) or file request_object. Read-only, no auth, no charge; same catalog snapshot as find_geometry.

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": {
      "sizes_mm": "<sizes_mm>"
    },
    "name": "find_by_dimensions"
  }
}

Input Schema

Name	Required	Description
`category`	No	Exact category from list_categories, to narrow the search.
`sizes_mm`	Yes	One to four measured sizes in mm, e.g. [40, 80] for a profile or [10.5] for a bore.
`tolerance_mm`	No	Allowed difference per size; default 0.5.

Output Schema

Name	Required	Description
`next`	No	What to call next.
`total`	Yes	Objects with at least one match.
`results`	Yes	Best matches first, at most 25.
`sizes_mm`	No	The sizes searched, as parsed.
`tolerance_mm`	No	Tolerance applied per size.

Schema Changelog

Changes observed during successful MCP inspections.

Changed19 schema fields changedOct 28, 2026
- changedInput schema / properties / category / description
```
Previous value: -"Optional exact category from list_categories to narrow the search."New value: +"Exact category from list_categories, to narrow the search."
```
- changedInput schema / properties / sizes_mm / description
```
Previous value: -"One to four sizes in mm, e.g. [40, 80] for a profile, [10.5] for a bore."New value: +"One to four measured sizes in mm, e.g. [40, 80] for a profile or [10.5] for a bore."
```
- changedInput schema / properties / tolerance_mm / description
```
Previous value: -"Allowed difference per size, default 0.5. Use about 0.2 for caliper readings of machined parts, 1 for rough measurements."New value: +"Allowed difference per size; default 0.5."
```
- addedOutput schema / properties / next / description
```
Added value: +"What to call next."
```
- addedOutput schema / properties / results / description
```
Added value: +"Best matches first, at most 25."
```
- addedOutput schema / properties / results / items / properties / all_overall_sizes_match / description
```
Added value: +"True when every size you gave matched an overall dimension."
```
- addedOutput schema / properties / results / items / properties / free_files / description
```
Added value: +"Free STEP/STL files on the object."
```
- addedOutput schema / properties / results / items / properties / matching_features / description
```
Added value: +"Feature matches, up to five."
```
- addedOutput schema / properties / results / items / properties / matching_features / items / additionalProperties
```
Added value: +true
```
- addedOutput schema / properties / results / items / properties / matching_features / items / description
```
Added value: +"A mating feature that matched: feature, exact size, what it mates with, fit class, and which of your sizes matched."
```
- addedOutput schema / properties / results / items / properties / name / description
```
Added value: +"Display name."
```
- addedOutput schema / properties / results / items / properties / overall_mm / additionalProperties
```
Added value: +true
```
- addedOutput schema / properties / results / items / properties / overall_mm / description
```
Added value: +"The object's overall size in mm."
```
- addedOutput schema / properties / results / items / properties / size_table_rows_matched / description
```
Added value: +"Rows of the object's size table containing a matching number."
```
- addedOutput schema / properties / results / items / properties / slug / description
```
Added value: +"Object slug for the other tools."
```
- addedOutput schema / properties / results / items / properties / url / description
```
Added value: +"Object page."
```
- addedOutput schema / properties / sizes_mm / description
```
Added value: +"The sizes searched, as parsed."
```
- addedOutput schema / properties / tolerance_mm / description
```
Added value: +"Tolerance applied per size."
```
- addedOutput schema / properties / total / description
```
Added value: +"Objects with at least one match."
```

Changed4 schema fields changedOct 22, 2026

changedInput schema / properties / category / description

Previous value: -"Optional exact category to narrow the search."New value: +"Optional exact category from list_categories to narrow the search."

changedInput schema / properties / sizes_mm / description

Previous value: -"Sizes in mm, e.g. [40, 80] for an outline, [10.5] for a bore, [47.5, 64] for a bore and a flange."New value: +"One to four sizes in mm, e.g. [40, 80] for a profile, [10.5] for a bore."

changedInput schema / properties / tolerance_mm / description

Previous value: -"How close a size must be, default 0.5 mm."New value: +"Allowed difference per size, default 0.5. Use about 0.2 for caliper readings of machined parts, 1 for rough measurements."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "next": {
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "all_overall_sizes_match": {
+            "type": "boolean"
+          },
+          "free_files": {
+            "type": "integer"
+          },
+          "matching_features": {
+            "items": {
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "name": {
+            "type": "string"
+          },
+          "overall_mm": {
+            "type": "object"
+          },
+          "size_table_rows_matched": {
+            "type": "integer"
+          },
+          "slug": {
+            "type": "string"
+          },
+          "url": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "slug",
+          "name"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "sizes_mm": {
+      "items": {
+        "type": "number"
+      },
+      "type": "array"
+    },
+    "tolerance_mm": {
+      "type": "number"
+    },
+    "total": {
+      "type": "integer"
+    }
+  },
+  "required": [
+    "total",
+    "results"
+  ],
+  "type": "object"
+}

AddedOct 22, 2026

TDQS

A4.4/5.0

Behavior3/5

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

Annotations already declare read-only, idempotent, closed-world and non-destructive, so the description's restatement of 'read-only, no auth, no charge' is partly redundant. It does add genuinely new behavioral context: the matching order-insensitivity, the ranking rules, the shared catalog snapshot with find_geometry, and the important fact that a no-match result is not an error. Those additions are useful but the safety-related statements duplicate the annotations.

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 and the sibling exclusion, and every sentence carries information (matching rules, ranking, no-match handling, tolerance guidance). It is dense and somewhat run-on in the parenthetical size and feature lists, which costs a point on structure but not on usefulness.

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?

An output schema exists, so return-value details are unnecessary; the description still covers the things schema cannot convey, such as match ordering, ranking priority, and what a non-matching result means. Nothing an agent needs to invoke this correctly is missing.

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 an extra point for the tolerance_mm heuristic (0.2 for caliper readings of machined parts, 1 for rough measurements), which gives an agent a concrete starting value the schema does not. It says nothing about the optional category parameter, so it stops short of 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 (identify) and the exact input resource (one to four measured sizes) plus examples of what those sizes might be (outline, bore, pin, flange). It explicitly names and rules out the sibling find_geometry, so an agent can pick between them without opening either schema.

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?

Gives an explicit when-to-use condition ('when you do not know its name'), names the alternative and the condition that selects it ('use find_geometry when you do'), and adds a fallback path (widen tolerance_mm or file request_object) when no match is returned.

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

All Xem Studio: Part Dimensions & CAD tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?