Skip to main content
Glama

Scaffold a site that passes the rulebook

init_site

Scaffold a new website into a folder by writing index.html, styles.css, and NOTES.md, with structure chosen to vary from previous scaffolds.

Instructions

Write index.html, styles.css and NOTES.md into a folder.

The page is built to come back clean from review_site: three theme states, neutrals that carry a trace of the anchor hue, press feedback with a hover guard, 48px touch targets, 16px inputs, minmax(0, 1fr) grid tracks, overflow-x: clip, no animation above the fold, no eyebrow, no emoji icons, no side stripes, no backdrop blur.

The structure is chosen from a local ledger of what was scaffolded last, so two consecutive sites differ in their SECTIONS, not only in their colours. That is the axis the research ranks highest and recolouring the axis it ranks lowest.

Every unwritten field is a visible, labelled hole rather than filler. Nothing is invented: no testimonials, no ratings, no counts, no press.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hueNoForce an anchor hue in OKLCH degrees, if you already know the colour.
nameNoThe name to put in the header. Defaults to a title-cased version of the subject.
forceNoOverwrite files that are already there. Default false.
recordNoRecord the choices in the local variety ledger. Default true. Turning it off means the next scaffold may repeat this shape.
subjectYesWhat the site is about, in a few words. For example: "chess lessons for club players, Brooklyn".
directoryYesFolder to write into. It is created if it does not exist, and must be empty or contain only files this tool wrote.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
fixNo
whyNo
nextNo
toolYesWhich tool produced this.
ledgerNo
statusYespass = checked and clean. fail = checked and found problems. skipped = nothing was measured. error = the tool could not run.
choicesNo
paletteNo
problemNo
headlineYesOne sentence verdict, safe to show a non-technical user.
directoryNo
anchor_hueNo
error_codeNoSet only when status is "error".
files_writtenNo
previous_choicesNo
differs_from_previousNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

B3.4/5.0
Behavior2/5

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

Annotations provide no safety hints (all false), so the description must carry the burden. It discloses that it writes three files and that content is not invented, but it omits key side effects: it does not mention that it may overwrite existing files when force=true, that it refuses to write into a non-empty directory unless the files were tool-written, or that it writes to a local ledger by default. These behaviors are only in the parameter schema, not the description.

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?

The description is front-loaded with the core action and then lists many specific design constraints. While the list is long, each item is a concrete rule an agent needs to know to scaffold a compliant site. It is structured into two coherent paragraphs with minimal fluff, though it could be tightened by moving some design details to a reference.

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?

Given the output schema exists, the description need not explain return values. It covers the main purpose and the design rules thoroughly, but it omits edge-case behavior (e.g., failure when directory is not empty, overwrite semantics) that are relevant to calling the tool correctly. For a scaffold tool with six parameters, a bit more operational context would help, but it is not severely incomplete.

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 description coverage is 100%, so the baseline is 3. The description does not add any parameter-specific meaning beyond the schema—it never mentions 'hue', 'name', 'force', 'record', or 'directory' semantics. It does reference the ledger concept, but that maps to the 'record' parameter without naming it. No added value.

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 description opens with a specific verb and resource: 'Write index.html, styles.css and NOTES.md into a folder.' The title 'Scaffold a site that passes the rulebook' reinforces the purpose. It clearly distinguishes from sibling tools like review_site or palette_from_subject, which are checks or helpers, not creators.

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?

The description implies this is the tool to use when you need a new site that will pass review_site ('The page is built to come back clean from review_site'). However, it never explicitly states when to use it vs alternatives, nor does it mention prerequisites or workflow ordering (e.g., 'use palette_from_subject first to choose a hue'). The context is implied, not explicit.

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