Skip to main content
Glama

Remove Page

remove_page
DestructiveIdempotent

Remove a page from the site. Cannot remove the home page. A backup of the current site is saved automatically before every removal (restorable via Site Backups in the Zarla editor) — the response reports it under "backup"; if backup.created is false with skipped_reason "snapshot_failed", warn the user the removal is NOT backed up.

Annotations: read-only=false, destructive=true, idempotent=true, open-world=false. Why: Deletes a page from the DRAFT — destructive; a backup of the site is saved first. Idempotent: a repeat finds nothing to remove and saves nothing. Closed-world. The live site changes only when the user confirms publish_site; the draft stays editable in the Zarla editor.

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>",
      "page_slug": "<page_slug>"
    },
    "name": "remove_page"
  }
}

Input Schema

NameRequiredDescriptionDefault
site_idYes
page_slugYesPage slug to remove

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare destructive=true, idempotent=true, and openWorldHint=false, so the safety profile is partly pre-supplied. The description earns credit above that baseline by disclosing the automatic site backup, its restore path in the Zarla editor, the 'backup' response field, and an explicit warning branch when backup.created is false with skipped_reason 'snapshot_failed'. That failure-handling detail is exactly the kind of behavior an agent cannot infer from structured fields, though the remaining traits largely restate the annotations.

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-loaded with the action and the key constraint, then the backup guarantee and the failure branch. Every clause carries information, though the long parenthetical about restore location and the quoted field names make the second sentence dense.

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?

There is no output schema, so the description correctly explains the meaningful part of the return value (the 'backup' object and its failure state) and pairs that with the destructive-removal and home-page constraints. For a two-parameter destructive tool, an agent has what it needs to call it and to report the outcome accurately.

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 coverage is only 50%: page_slug carries a one-line schema description and site_id carries none. The description never discusses either parameter and adds no slug format guidance (e.g., whether to pass 'about' or '/about'), so it only indirectly informs page_slug via the home-page exclusion rule. It does not compensate for the coverage gap.

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 ('Remove a page from the site') plus an immediate scope boundary ('Cannot remove the home page'). The resource noun cleanly separates it from sibling operations like add_page, get_page, and remove_block without needing the schema.

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?

Gives a concrete when-not-to-use rule (home page is not removable), which prevents a predictable failed call. It does not name alternatives or state prerequisites (e.g., that the page must exist in the current draft, or how to find a slug), so it falls short of a 5.

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.