Skip to main content
Glama

Components Arrange

components_arrange
Destructive

Aligns or distributes selected page components within their selection bounds and previews conflict-checked coordinate updates while preserving sizes, styles, and layers.

Instructions

Align or distribute unrotated, ungrouped leaf components on a static page.

Align 2–100 objects against their selection bounds, not canvas bounds. Distribute 3–100 objects with equal edge gaps, holding first/last positions fixed. Negative gaps (overlap) are allowed. Stable position ties preserve input ID order. Computed coordinates truncate toward zero to integer pixels as updatePage does; preview includes requested and persisted coordinates. Sizes, opposite-axis positions, styles and layers remain unchanged. report_refresh first; page_get fingerprint; one versioned page write with preview/read-back/journal/undo. Groups/responsive are separate.

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": {
      "page_id": "<page_id>",
      "component_ids": "<component_ids>",
      "action": "<action>",
      "expected_fingerprint": "<expected_fingerprint>"
    },
    "name": "components_arrange"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
dry_runNo
page_idYes
report_idNo
component_idsYes
expected_fingerprintYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the destructive/not-readOnly annotations, it discloses what actually happens: one versioned page write with preview/read-back/journal/undo, dry_run-based preview containing requested and persisted coordinates, truncation toward zero to integer pixels matching updatePage, negative gaps permitted, stable tie ordering, and an explicit statement that sizes, opposite-axis positions, styles and layers are untouched. That is exactly the kind of blast-radius and side-effect detail annotations cannot convey.

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 the core purpose, then constraints, then workflow, then non-effects — a logical order with no filler sentences. The telegraphic shorthand ('report_refresh first; page_get fingerprint') is efficient but slightly cryptic and packs multiple facts per clause, which costs a bit of readability.

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 six-parameter mutating tool, the description covers scope, limits, ordering, side effects and non-effects, and an output schema exists so return values need no explanation. The remaining gap is that it never names which tool handles the excluded group/responsive cases, leaving the agent to infer routing.

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 0%, so the description must carry the load, and it largely does: action semantics via align vs distribute and their object-count bounds, dry_run as preview, expected_fingerprint sourced from page_get, and report_id implied by 'report_refresh first'. It stops short of explaining each individual parameter (e.g. page_id, the exact enum choices) but compensates well above the baseline for a 0%-coverage 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 first sentence names specific verbs (align/distribute) and a precisely scoped resource (unrotated, ungrouped leaf components on a static page). The closing note 'Groups/responsive are separate' explicitly carves out the cases this tool does not handle, letting an agent distinguish it from geometry/sibling tools without opening a 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 concrete selection thresholds (align 2–100, distribute 3–100) and a required workflow (report_refresh first, page_get for the fingerprint, then a single versioned write), which tells the agent when the tool applies and in what order to call prerequisites. It does not name the specific sibling that handles groups/responsive, only that they are 'separate', so routing to an alternative is left implicit.

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