Skip to main content
Glama

Website: save a version and check the design

website_save

Save a version of the client's new website and run the design check. Give the business details, sourced facts, the pages (each: slug, '' for home; title up to 60 characters; description 50-160; nav_label for the menu, 6 at most; sections) and a style: Straightforward, Bold or Classic, optionally with the client's accent colour, or exact tokens. Sections: hero {heading, sub, image_url, image_alt, cta_label}, services {heading, items[{name, text, page, image_url}]}, proof {heading, reviews[{quote, name, source}], rating{value, count, source}}, gallery {heading, images[{url, alt}]}, areas {heading, towns[], text}, process {heading, steps[{name, text}]}, faq {heading, items[{q, a}]}, text {heading, body}, cta {heading, sub, cta_label}, quote_form {heading, sub, button_label}. Reviews and ratings appear only when they are in facts (the quote, or the rating and count, with where they came from: gbp_reviews / gbp_profile). Fields left out keep their last version. When the check passes it returns the preview link, the client's approval link and the download; when it doesn't, it says what to fix (in order) and the preview keeps showing the last version that passed.

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": {
      "client": "<client>"
    },
    "name": "website_save"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoWhat changed in this version
factsNoEach number or claim the site makes, with where it comes from
pagesNo
styleNo
accentNoHex colour, e.g. the client's brand colour #2e6b3f
clientYes
tokensNo
businessNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only declare non-read-only, non-idempotent, non-destructive, open-world; the description goes well beyond that by disclosing partial-update semantics ('Fields left out keep their last version'), a validation gate with ordered fix instructions, and the fact that the live preview continues serving the last passing version on failure. That is exactly the mutation and failure behavior an agent needs. It omits permission/auth requirements and any rate or size limits, which keeps it from a 5.

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

Conciseness3/5

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

The intent is front-loaded in the first sentence, and the long section enumeration largely earns its place because the schema does not describe section internals. But the whole thing is a single unstructured paragraph with heavy nesting of braces and parentheticals, making it hard to scan; splitting the section type list or the failure behavior into separate lines would preserve content while improving parseability.

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 an 8-parameter nested tool with no output schema, the description covers the hard parts: section composition, style selection, accent/tokens alternative, facts sourcing rules, and the full return contract for both success and failure. The remaining gaps are the business object's fields (name, phone, city, hours, lead_form_id) and token keys, which are self-explanatory from their schema names.

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 description coverage is only 38% and the schema leaves section objects as additionalProperties, so the description carries real weight: it documents page slug/title/description/nav_label constraints (60 chars, 50-160, 6 nav items max), enumerates all ten section types with their inner field names, and explains the facts dependency for reviews and ratings. It adds little for note, tokens and the business fields beyond 'Give the business details', which prevents a 5.

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 opening sentence names a specific verb and resource: 'Save a version of the client's new website and run the design check.' It clearly bundles persistence plus validation, which an agent can distinguish from siblings like website_status or website_launch. It stops short of explicitly naming which sibling to use instead when the goal is only to inspect or publish.

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?

Usage is implied by describing the pass/fail outcome ('when the check passes it returns the preview link...when it doesn't, it says what to fix'), which tells the agent this is the pre-publish validation step. However, there is no explicit when-to-use/when-not guidance and no named alternative for cases such as regenerating or editing without saving a version, so the agent must infer the workflow position.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.