Skip to main content
Glama

Save a page or a post

website_save_page

Create or change a page of the draft, matched by path ("" is the home page, "about", "services/cleaning"); only what is passed changes, and sections replace all of the page's sections. A page is made of sections; a blog post (kind "post", path = its slug) has a Markdown body and a date, and lives at /blog/. nav puts the page in the menu with that label. Images are image file_ids from the file store; in Markdown write alt. Sections, each {"type": ...}: hero {heading, text, image, image_alt, buttons [{label, link}] (up to 2), layout "center" | "split"}; text {heading, body (Markdown)}; features {heading, text, items [{title, text}]}; image {image, alt, caption, size "normal" | "wide"}; gallery {heading, images [{image, alt, caption}]}; pricing {heading, text, plans [{name, price, period, description, features [..], button, highlight, label (above a highlighted plan; default "Most popular" in the site's language)}]}; testimonials {heading, items [{quote, name, role}]}; faq {heading, items [{question, answer (Markdown)}]}; cta {heading, text, button}; stats {heading, items [{value, label}]}; logos {heading, images [{image, alt}]}; contact {heading, text, email, phone, address, form (a form's slug), button_label}; booking {heading, text, meeting (a meeting type's slug), button_label}; newsletter {heading, text, newsletter (its slug), button_label}; posts {heading, count} lists the latest blog posts. Images are image file_ids from the file store, with alt text. A link is a page of the site ("/about"), https://..., mailto: or tel:. Optional on any section: id (for "#links") and background "plain" | "tinted" | "brand". Costs $0.01 per call; nothing if it fails.

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": "<site>",
      "path": "<path>"
    },
    "name": "website_save_page"
  }
}

Input Schema

NameRequiredDescriptionDefault
navNoThe page's label in the menu; "" takes it out.
bodyNoPosts: Markdown.
dateNoPosts. Default today.
kindNopage
pathYes
siteYesThe site's name, as in cncto.co/w/<name>.
imageNoA file_id: the image shown when the page is shared, and a post's cover.
titleNo
sectionsNoSections, each {"type": ...}: hero {heading, text, image, image_alt, buttons [{label, link}] (up to 2), layout "center" | "split"}; text {heading, body (Markdown)}; features {heading, text, items [{title, text}]}; image {image, alt, caption, size "normal" | "wide"}; gallery {heading, images [{image, alt, caption}]}; pricing {heading, text, plans [{name, price, period, description, features [..], button, highlight, label (above a highlighted plan; default "Most popular" in the site's language)}]}; testimonials {heading, items [{quote, name, role}]}; faq {heading, items [{question, answer (Markdown)}]}; cta {heading, text, button}; stats {heading, items [{value, label}]}; logos {heading, images [{image, alt}]}; contact {heading, text, email, phone, address, form (a form's slug), button_label}; booking {heading, text, meeting (a meeting type's slug), button_label}; newsletter {heading, text, newsletter (its slug), button_label}; posts {heading, count} lists the latest blog posts. Images are image file_ids from the file store, with alt text. A link is a page of the site ("/about"), https://..., mailto: or tel:. Optional on any section: id (for "#links") and background "plain" | "tinted" | "brand".
nav_orderNo
descriptionNoFor search engines and link previews.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations, the description discloses important behavior: only passed fields change, sections replace all existing page sections, posts get a Markdown body and dated /blog/<slug> location, and the call costs $0.01 unless it fails. These details materially affect how an agent should invoke the tool.

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 description is front-loaded with the core behavior, but it becomes a very long run-on block and repeats the image file_id rule twice. Much of the detailed section schema duplicates the input schema's sections description, so not every sentence earns its place.

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 a complex save tool with annotations and no output schema, the description covers the essential invocation details: draft page/post behavior, path matching, section replacement, images, nav, and cost. It could still say more about prerequisites or the response, but it is largely complete for correct invocation.

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?

With only 64% schema description coverage, the description adds useful meaning for path, nav, body, date, image, and the page-versus-post distinction. It still leaves nav_order and title/description largely to the schema, and the long section list duplicates the schema's own sections description.

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 gives a specific verb and resource: create or change a page of the draft, matched by path. It clearly distinguishes pages from blog posts by kind, path, body, and date, so an agent can identify the operation without opening sibling schemas.

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?

The description explains the main usage context: saving into the draft, matching by path, and using kind "post" for blog posts. It does not explicitly name alternatives such as website_delete_page or website_publish, but the conditions for using this tool are otherwise clear.

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.

Resources