Skip to main content
Glama

update_site

Update site-wide settings like global CSS, head HTML, robots.txt, GDPR banners, and maintenance mode. Only supplied fields change, so other settings remain untouched.

Instructions

Update site-wide settings. Only provided fields change. global_css applies to every page; head_js is raw HTML injected into (use it for / tags such as fonts and analytics).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
head_jsNoRaw <head> HTML: script and link tags
global_cssNo
robots_txtNo
gdpr_configNoCookie banner colours as hex strings
test_domainNoSubdomain under the CMS host where the site is served for review, e.g. "saolcapital" -> saolcapital.<cms host>. Lower-case slug, must be unique.
theme_colorsNoComma-separated hex colours exposed as CSS variables
blog_list_classNoClasses for the wrapper around the items, e.g. "row py-4"
blog_date_formatNoPHP date format for {{date}}, e.g. "F jS"
maintenance_modeNo
enable_gdpr_popupNo
blog_item_templateNoHTML for one blog list item. Placeholders: {{title}} {{url}} {{date}} {{image}} {{read_time}} {{excerpt}} {{author}} {{subtitle}} {{tags}}; sections {{#image}}...{{/image}} and {{^image}}...{{/image}}. The first element gets class blog-post automatically. Empty = default article list.
recaptcha_public_keyNo
recaptcha_secret_keyNoRequired for the built-in contact form endpoint (reCAPTCHA; v2 invisible or v3)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It does add real value by disclosing partial-update semantics ('Only provided fields change') and by warning that head_js injects raw HTML into <head>, which is a security-relevant detail. It omits permissions/auth requirements, reversibility, and any side effects of maintenance_mode or recaptcha changes.

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?

Three tight sentences, front-loaded with purpose, followed by the update semantics and the two most nuanced parameters. Every sentence contributes, though the final sentence is somewhat param-specific and could be marginally tighter.

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

Completeness3/5

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

For a 13-parameter mutation tool with a nested object, no annotations, and no output schema, the description covers only the partial-update behavior and two parameters. Permission requirements and the effects of enabling maintenance_mode or gdpr_popup are left unexplained, so the coverage is adequate but incomplete.

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 62%, so the schema already documents several parameters. The description meaningfully supplements global_css (schema has no description) by stating it applies to every page, and reinforces head_js usage, but says nothing about the other eleven parameters, including the nested gdpr_config object.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource, 'Update site-wide settings', which is unambiguous. However, it does not distinguish itself from sibling tools that also mutate site-level configuration, notably set_favicon and set_logo, leaving the boundary between them to inference.

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

Usage Guidelines2/5

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

There is no explicit guidance on when to use this tool versus set_favicon, set_logo, or update_booking_setup. The phrase 'Only provided fields change' hints at partial-update behavior but is not framed as usage direction, and no prerequisites or exclusions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.