Extrabold Tools Gridfinity

Get Gridfinity Grid Questions

get_gridfinity_grid_questions

Read-onlyIdempotent

Return the next Gridfinity baseplate configuration questions to ask, using Extrabold Tools setting descriptions and dependencies.

Input Schema

Name	Required	Description
`rows`	No
`columns`	No
`version`	No
`tolerance`	No	Experimental fit setting saved per printer. For dovetails, 0 mm gives the largest male tab; higher values make it smaller, up to 0.5 mm. Also affects CLICKbase clips and magnet holes. Print the tolerance test package to choose a dovetail fit. Normal bin pockets keep fixed geometry; the included bin-fit sample is a reference check. Values: none = 0 mm, tight = 0.1 mm, standard = 0.2 mm, loose = 0.3 mm, very-loose = 0.4 mm, extra-loose = 0.5 mm.
`linkOrigin`	No
`marginType`	No
`borderRadius`	No
`magnetHeight`	No
`baseplateType`	No
`gridUnitDepth`	No
`gridUnitWidth`	No
`plateMarginMm`	No
`screwHeadSize`	No
`screwHoleSize`	No
`splitStrategy`	No
`toggleMagnets`	No
`magnetDiameter`	No
`partsConnector`	No	Experimental dovetails interlock split pieces without separate parts and use your printer tolerance for male tabs. They require Split to Build Plates and work with all baseplate types. Clips connect split seams and optional outer edges; the printable clip model is included (not compatible with Skeleton).
`magnetDirection`	No
`magnetHoleStyle`	No
`splitOffMargins`	No
`toggleScrewHoles`	No
`splitToBuildplates`	No
`connectMarginCrossings`	No	Also place a dovetail wherever a split edge crosses from grid cells into a margin region. Off: dovetails only at cell-to-cell crossings.
`removeHolesOnSplitLines`	No
`toggleMagnetReleaseHole`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 8, 2026

addedInput schema / properties / connectMarginCrossings

Added value: +{
+  "description": "Also place a dovetail wherever a split edge crosses from grid cells into a margin region. Off: dovetails only at cell-to-cell crossings.",
+  "type": "boolean"
+}

addedInput schema / properties / partsConnector / description

Added value: +"Experimental dovetails interlock split pieces without separate parts and use your printer tolerance for male tabs. They require Split to Build Plates and work with all baseplate types. Clips connect split seams and optional outer edges; the printable clip model is included (not compatible with Skeleton)."

addedInput schema / properties / tolerance / description

Added value: +"Experimental fit setting saved per printer. For dovetails, 0 mm gives the largest male tab; higher values make it smaller, up to 0.5 mm. Also affects CLICKbase clips and magnet holes. Print the tolerance test package to choose a dovetail fit. Normal bin pockets keep fixed geometry; the included bin-fit sample is a reference check. Values: none = 0 mm, tight = 0.1 mm, standard = 0.2 mm, loose = 0.3 mm, very-loose = 0.4 mm, extra-loose = 0.5 mm."

Changed1 schema field changedAug 12, 2026
- addedInput schema / properties / splitOffMargins
```
Added value: +{
+  "type": "boolean"
+}
```
First observedAug 5, 2026

TDQS

C2.3/5.0

Behavior2/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's remaining burden is to explain the interaction model. The vague clause 'using Extrabold Tools setting descriptions and dependencies' does not say how questions are sequenced, whether the supplied parameters change the returned set, or how the caller knows it is done.

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?

A single front-loaded sentence with no filler; it is not verbose. The brevity is a weakness in substance rather than a structural flaw, which is captured in the other dimensions.

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

Completeness2/5

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

For a tool with 26 configuration parameters, no output schema, and only safety annotations, the description is far too thin. It does not explain the shape of the returned questions, the termination condition, or the role of the passed-in settings — the agent cannot confidently call this correctly.

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

Parameters1/5

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

There are 26 parameters at only 12% schema description coverage, and the description adds nothing about any of them — not even that the already-supplied settings (rows, columns, baseplateType, tolerance, etc.) determine which questions are returned next. With this many undocumented inputs, the description fails to compensate for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Return the next ... configuration questions to ask'), which is better than a tautology, but the actual purpose of the tool — driving a step-by-step configuration wizard — is only implied. It never distinguishes itself from the generate_* siblings or explains why an agent would fetch questions instead of generating a baseplate directly.

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

Usage Guidelines2/5

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

There is no guidance on when to call this versus the five generate_* / find_* siblings, nor any prerequisite such as 'call repeatedly until no questions remain'. The agent must infer the interactive loop entirely on its own.

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

All Extrabold Tools Gridfinity 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?