Skip to main content
Glama
Sign In
handmade

handmade

by h-hiram
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

handmade_check

Checks UI changes against handmade.system.json and returns PASS or FAIL, listing fixes so all fonts, colors, sizes, radii, and spacing values pass.

Instructions

The finish gate for UI work. Returns PASS or FAIL. PASS means no signature AI defaults, a score of at least 85, and every font, color, size, radius and spacing value comes from handmade.system.json. Call it after every UI change. You are NOT done until it returns PASS. On FAIL, fix every listed item and call it again. After 5 rounds without PASS, stop and show the user what still fails. Use render=true with a URL (for example http://localhost:3000) for apps whose styles are built at runtime.

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": {
      "path": "<path>"
    },
    "name": "handmade_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesAbsolute path to a folder or file or a URL when render is true.
ignoreNoComma-separated tell IDs to skip. Only with the user's agreement.
renderNoCheck the rendered page in headless Chrome.
min_scoreNo
system_pathNoAbsolute path of handmade.system.json. Found automatically if omitted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the return shape (PASS/FAIL), the exact acceptance criteria, that failures are itemized, and the retry ceiling before escalation. It does not state whether the tool is read-only or writes any artifact, nor that headless-Chrome rendering is slower/heavier — the main remaining behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads purpose and outcome, then the procedural rules, then an advanced-mode tip. Every sentence carries an actionable instruction with no filler or repeated information.

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?

Given a 5-parameter, annotation-free tool with no output schema, the description is largely sufficient: outcome, acceptance criteria, retry policy, and the render mode are all covered. Minor gaps remain — what a 'tell ID' is for the ignore parameter, and whether the check has side effects or performance cost.

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 80%, so the baseline is 3, but the description adds genuine meaning: it explains the URL form of path and the runtime-styles condition under which render=true applies, and ties the score threshold to min_score. System_path and ignore receive nothing beyond their schema text, so it is not fully compensating.

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?

Opens with a specific role — 'The finish gate for UI work' — and immediately defines the concrete outcome: returns PASS or FAIL, with PASS meaning no signature AI defaults, a score of at least 85, and all font/color/size/radius/spacing values sourced from handmade.system.json. An agent can distinguish this from siblings like handmade_scan or handmade_list_tells purely from this text.

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?

Explicitly directs when to call ('after every UI change'), states the loop condition ('NOT done until it returns PASS'), prescribes the FAIL remediation path, and gives a termination rule ('after 5 rounds without PASS, stop and show the user what still fails'). It also routes the agent conditionally to render=true for apps whose styles are built at runtime, which is a real alternative-mode decision.

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