Skip to main content
Glama

Update Header

update_header
DestructiveIdempotent

Update the site header — navigation, CTA button, layout variant, announcement bar, logo size, background colour. The header appears on every page.

Annotations: read-only=false, destructive=true, idempotent=true, open-world=false. Why: Overwrites the draft's header and navigation settings — non-additive, so destructive by the MCP definition; idempotent; 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>"
    },
    "name": "update_header"
  }
}

Input Schema

NameRequiredDescriptionDefault
ctaNoHeader CTA button (e.g. "Get a Free Quote")
site_idYes
variantNo
logo_sizeNoHeader logo size — "small" | "medium" (default) | "large". Sizes the logo image or business-name text on every layout, desktop and phones. "Bigger" = one step up from the current size (read_site → header.logo_size).
nav_itemsNo
backgroundNoHeader background (ZAR-2060) — "default" (the page colour) | "alt" (soft) | "primary" (the brand colour) | "dark" (dark surface). Null clears it back to the page colour. Choosing a preset also clears any custom colour (a custom colour would otherwise win). Links, the phone, the logo text and the phone menu adapt automatically. A see-through / transparent header is not supported.
show_phoneNoShow phone number in header
background_colorNoCustom header colour as a 6-character hex (e.g. "#0f172a"); overrides the preset. Null clears it. Text adapts automatically (read_site → header.background / header.background_color).
announcement_itemsNoAnnouncement strip shown above the header on every page, e.g. ["Free shipping over $80", "Ships Australia-wide"]. Null or empty clears it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare destructive, idempotent, and closed-world, but the description adds genuinely non-redundant context: the header renders on every page (blast radius), the write lands in the draft not the live site, and publish_site is the confirmation gate. It stops short of saying what happens to existing header fields when only site_id is supplied, which matters for a destructive overwrite.

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?

Two tight sentences: the capability and its field inventory come first, the cross-page impact second. Nothing is padded, and the annotation rationale is kept separate and structured rather than bloating the prose.

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 9-parameter, nested-object mutation with no output schema, the description covers scope, draft-vs-live behavior, and the full field inventory. The remaining gap is partial-update semantics — whether omitted fields are preserved or cleared — which is exactly the ambiguity an agent needs resolved before calling a destructive tool.

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 67% and the schema itself carries rich descriptions for logo_size, background, background_color, and announcement_items, so the baseline of 3 applies. The description's field list largely mirrors the schema, and it adds no semantics for the one undocumented parameter (nav_items, including its nested children) beyond the word "navigation".

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 ("Update the site header") and immediately enumerates the six sub-areas it governs — navigation, CTA, layout variant, announcement bar, logo size, background colour. That enumeration matches the schema properties, so an agent can tell this is the header-settings tool rather than update_footer, update_design, or switch_design without opening any schema.

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 the resource scope, and the annotation rationale usefully notes that live-site impact is gated behind publish_site and that the draft remains editable. But there is no explicit when-to-use guidance and no routing against plausible alternatives such as update_design (global styling) or switch_design (layout overhaul), which an agent could easily confuse with changing header variant or background.

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.