Skip to main content
Glama

Publish Site

publish_site
Destructive

Publish the site to make it live on the web. Generates final HTML, optimizes for production, and deploys to CDN. Takes 5-15 seconds. This replaces whatever is currently live at the site's URL with the current draft — each publish is kept as a version in Site Backups. Publishing is included on paid plans only: if this site's plan doesn't include it, the call returns a plan handoff instead of publishing — a message and a link (its shape varies by host). Relay both to the user; don't retry the call.

Annotations: read-only=false, destructive=true, idempotent=false, open-world=true. Why: Replaces whatever is currently live with the draft — destructive AND open-world, because the result is on the public web. Not idempotent: every publish records a new published version in Site Backups and refreshes the site's scores, even for an unchanged draft. Hosts should confirm this one.

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": {
      "site_id": "<site_id>"
    },
    "name": "publish_site"
  }
}

Input Schema

NameRequiredDescriptionDefault
site_idYesThe site ID to publish

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare destructive, non-idempotent, and open-world, and the description adds substantially beyond that: a 5-15 second duration, that the live URL's content is overwritten with the draft, that each publish is retained as a version in Site Backups, and that non-qualifying plans return a handoff message whose shape varies by host. This is exactly the operational context an agent needs before invoking a destructive deploy.

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?

Three sentences, front-loaded with purpose and effect, then timing, then the plan-gating failure mode with the non-retry instruction last. No sentence is filler; each carries distinct information (side effect, duration, version retention, error handling).

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

Completeness5/5

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

For a one-parameter destructive deploy with no output schema, the description covers the essentials: what gets replaced, latency expectations, persistence of versions, and how a failed plan-gated call manifests. Nothing an agent needs in order to invoke it correctly or interpret failure is absent.

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?

There is a single required parameter with 100% schema description coverage and a UUID format pattern, so the schema fully documents it. The description adds no additional semantics about site_id, which is the expected baseline when the schema carries the load.

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 ('Publish the site to make it live on the web') and immediately clarifies the effect: generating final HTML, optimizing, and deploying to a CDN. It also implicitly distinguishes publishing from previewing by contrasting the live URL with 'the current draft', so an agent can tell it apart from show_site_preview.

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

Usage Guidelines4/5

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

It gives clear conditions for use (making the draft live) and an explicit don't: on a plan handoff, relay the message and link to the user and do not retry. What's missing is any explicit mention of a preview-first alternative, but the guidance it does give is actionable and unambiguous.

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.