Skip to main content
Glama
bhanutpt

inksmcp

by bhanutpt

split

Divide a region into named cells for comic panels, dashboard tiles, poster columns, or table grids, returning cell IDs and coordinates for use as layout targets.

Instructions

Divide a region into named cells — comic panels, dashboard tiles, poster columns, table grids — without computing any positions. region: "page", an element id (its measured box) or [x, y, w, h]; margin insets it (one number, [vertical, horizontal] or [top, right, bottom, left]). rows: one entry per row, either a number of equal columns or a list of column ratios, e.g. [[2, 1], [1, 1], [1, 2]]; heights: row ratios (default equal); gutter: space between cells (number or [horizontal, vertical]). Creates one rect per cell, -1, -2, ... row by row, in layer — invisible unless style gives e.g. {"fill": "#fff", "stroke": "#000", "stroke_width": 0.6, "rx": 2}. Use the ids as targets: clip ("clip": "cell-5"), align/layout ("to": "cell-2"), place, fit, connect. An element region is its measured box (stroke included). Tables: split the header strip into columns (e.g. rows [[3, 1, 1]]), then repeat the data rows with step [0, row pitch] and texts at the returned column edges (numbers: text_anchor end at the right edge). Returns the cells [x, y, w, h] and their ids per row.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
rowsYes
layerNoCells
styleNo
doc_idNo
gutterNo
marginNo
regionNopage
heightsNo
previewNo
id_prefixNocell

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 burden and does well: it discloses that one rect is created per cell with sequential ids row by row, that they are placed in `layer`, that they are 'invisible unless style' supplies a fill/stroke, and that an element region is its measured box (stroke included). It omits permission/undo/error behavior, so not a 5.

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 'no positions' value proposition are front-loaded, and the rest is dense with concrete examples rather than filler. The multi-idea sentences (spec parsing plus workflow plus return values) run long, but nearly every clause earns its place.

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 a 10-parameter mutation tool with no annotations and no output schema, the description covers the essential semantics, explains the return value ('returns the cells [x, y, w, h] and their ids per row'), and supplies a worked table recipe. doc_id and preview remain unexplained, leaving a modest gap.

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 description coverage is 0%, so the description must compensate — and it does, explaining region forms, margin/gutter accept scalar or tuple, rows as counts or ratio lists, heights as row ratios, style fields, and id_prefix via the '-1, -2' example. Two parameters, doc_id and preview, are undocumented anywhere.

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 effect — 'Divide a region into named cells — without computing any positions' — then anchors it with concrete use cases (comic panels, dashboard tiles, poster columns, table grids). An agent can distinguish this from the sibling 'grid' and 'layout' tools from the opening clause alone.

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 strong usage context: the 'without computing any positions' framing, the guidance to consume the returned ids as targets for clip/align/place/fit/connect, and a concrete table workflow ('split the header strip... then repeat the data rows'). It stops short of an explicit 'use this instead of grid when...' exclusion, so it is clear context rather than full routing.

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