Skip to main content
Glama

Website: start a new site or redesign

website_start
Read-onlyIdempotent

Start a new website or a redesign for a client (the agency signed them for web design). Reads what exists first: the current site's pages, the searches and pages that bring Search Console clicks (those addresses must survive or redirect) and the search plan. Returns what was read, the questions to ask the agency or client, and the next steps. Then build with website_save. Reads only.

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_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
clientYesClient name from list_clients
current_siteNoThe client's current website, if not on file

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover safety (readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true), and the description reinforces rather than contradicts them with 'Reads only.' Beyond that it discloses what is actually gathered (current pages, Search Console click-driving searches and pages, the search plan), the hard constraint that clicked addresses must survive or redirect, and what comes back (findings, questions for agency/client, next steps). Minor gaps: no error/unknown-client behavior.

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 action and keeps the read/build split clear, with the constraint about surviving addresses highlighted. The middle sentence stacks several clauses and a parenthetical, which makes it denser than necessary, but nothing is genuinely wasted.

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 no output schema, the description helpfully sketches the return payload (what was read, questions to ask, next steps) and points to website_save for the follow-up action. It is complete enough to invoke correctly, with only edge-case behavior (missing client, no existing site) left implicit.

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% and both parameters are documented in the schema ('client' sourced from list_clients, 'current_site' if not on file). The description adds only contextual framing (the client is an agency web-design client, the current site's pages get read), not new syntax or formatting meaning, so baseline 3 applies.

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?

States a specific verb and resource ('Start a new website or a redesign for a client') and explicitly scopes it to agency web-design clients. It also names its sibling boundary by saying 'Then build with website_save', so an agent can distinguish the read/planning step from the build step without opening either schema.

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?

Gives the condition for use (agency signed the client for web design), the excluded work (building, delegated to website_save), and the sequencing rule ('Reads what exists first'). Alternatives and when-not are both explicit.

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.