Skip to main content
Glama

Components Geometry

components_geometry
Destructive

Set absolute pixel positions and sizes for 1–100 ungrouped top-level components in one previewed page write, preserving unspecified geometry and supporting restore.

Instructions

Set absolute pixel positions/sizes for 1–100 components in one page write.

Only ungrouped top-level leaf components on a static canvas. Load the page with report_refresh first; use page_get's fingerprint. Unspecified geometry and all unknown fields are retained. Values truncate toward zero to whole pixels; preview shows requested and after values. Dimensions must remain at least one pixel. Does not scale children, change layers, or change rotation. Supports preview, durable journal, independent read-back and operation_restore.

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>",
      "changes": "<changes>",
      "expected_fingerprint": "<expected_fingerprint>"
    },
    "name": "components_geometry"
  }
}

Input Schema

NameRequiredDescriptionDefault
changesYes
dry_runNo
page_idYes
report_idNo
expected_fingerprintYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A4.1/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing what is preserved (unspecified geometry and unknown fields), rounding behavior (truncate toward zero), the one-pixel minimum, preview output (requested vs after values), what is not propagated (children, layers, rotation), and the recovery path (journal, read-back, operation_restore). That is exactly the mutation context an agent needs on a destructiveHint=true 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?

Front-loads the operation and bounds in sentence one, then lays out prerequisites and edge behaviors in short, scannable clauses. A few fragments are telegraphic enough to need a second read, and the trailing 'Supports preview, durable journal, independent read-back and operation_restore' is somewhat listy.

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 destructive multi-item mutation with an output schema, the description covers prerequisites, eligibility constraints, rounding, minimums, and recovery. The remaining gap is the role of report_id and the exact meaning of page_id versus fingerprint, which an agent must infer.

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

Parameters3/5

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

With 0% schema description coverage the description must carry parameter meaning, and it explains the changes array bound (1–100), dry_run via 'preview', and expected_fingerprint via page_get. However, report_id is never mentioned, component_id semantics are unstated, and null-vs-omitted behavior is only obliquely covered by 'unspecified geometry and all unknown fields are retained.'

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

Purpose4/5

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

Opens with a specific verb and resource plus scope: 'Set absolute pixel positions/sizes for 1–100 components in one page write.' The constraints ('only ungrouped top-level leaf components on a static canvas') implicitly separate it from siblings like components_patch or components_arrange, but no sibling is named to make the boundary explicit.

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 concrete preconditions and ordering: load the page with report_refresh first, then use page_get's fingerprint. The 'only ungrouped top-level leaf components on a static canvas' clause functions as an explicit exclusion. It stops short of naming which sibling to use for grouped, nested, or rotated components.

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