Skip to main content
Glama
Sign In
handmade

handmade

by h-hiram
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

handmade_fix_plan

Scan an existing UI and return a file-by-file repair plan for AI-design tells, with fixes and a design system built from the project's own tokens.

Instructions

Scan an existing UI and return a repair plan: every AI-design tell by file and line, its fix and a design system built from the project's own tokens. Apply it to change only the visual layer.

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_fix_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoType of screen. Detected if omitted.
moodNoOverall feel.
pathYesAbsolute path to the project or folder.
allowNoComma-separated deliberate brand choices the rules should keep, for example 'purple'. Only when the user confirms it is their brand.
ignoreNoComma-separated tell IDs or categories to skip.
productNoWhat the product is, in one line.
variantNoPick an alternative generated design system.
audienceNoWho uses it and where.
referenceNoA site, magazine, place or object the user likes.
signatureNoThe one thing people should remember about the screen.
save_system_toNoAbsolute path to write handmade.system.json (usually the project root). handmade_check reads it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations, the description carries the full behavioral burden, and it leaves the most consequential question unresolved: whether this tool edits source files or only produces a plan. 'Apply it to change only the visual layer' reads either as a guarantee of scope or as a write operation, and the schema's save_system_to shows it does write at least one file. Nothing is said about permissions, runtime, or reversibility, so an agent cannot judge the blast radius of calling it.

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?

Two sentences, front-loaded with the action and the deliverable, and the colon list is an efficient way to enumerate the three outputs. The closing sentence is the weak point — it is short but ambiguous about whether a write occurs, so brevity costs clarity there.

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

Completeness3/5

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

For an 11-parameter tool with no output schema, the description does sketch the return shape (tells, fixes, token-based system), which is genuinely useful. Gaps remain around persistence (save_system_to writing handmade.system.json and its dependency on handmade_check), mutation scope, and the workflow position relative to the four sibling tools. Adequate but not complete for a tool of this complexity.

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?

Schema coverage is 100% across all 11 parameters, so the baseline is 3. The description does add a little: 'design system built from the project's own tokens' gives context for variant and save_system_to, and 'every AI-design tell' explains ignore semantically. It does not address how allow, signature, or reference influence the plan, so it does not exceed the schema.

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?

The description pairs a specific verb with a specific artifact: scan a UI, return a repair plan listing every AI-design tell by file and line with fixes, plus a design system derived from the project's own tokens. That is far more informative than a tautology, and the 'repair plan' framing implicitly separates it from a plain scan. It stops short of naming any sibling (handmade_scan, handmade_check, handmade_list_tells), so the agent must infer the boundary itself.

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

Usage Guidelines3/5

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

'Scan an existing UI' and 'Apply it to change only the visual layer' imply the situation — an existing project needing visual remediation rather than a new design — but there is no explicit when-not or named alternative. The agent is not told, for instance, whether to run handmade_scan or handmade_list_tells first, or when handmade_design_brief is the better entry point. Usage is implied rather than stated.

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