Mark

Save Site

save_site

Idempotent

Adds or edits a website: hostname, name, whether it is primary, and lead-capture settings for the site tag. Pass siteId to edit. Changing a site's hostname clears its AI readiness score and site audits. Related: list_sites, delete_site.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "save_site"
  }
}

Input Schema

Name	Required	Description
`name`	No	Display name for the site.
`domain`	No	Bare hostname, e.g. example.com. Required when adding.
`siteId`	No	Existing site id. Omit to add.
`capture`	No	Lead-capture config: capture.kind selector\|hubspot, honeypotField, gtmContainerId, cookiebotId, consentMode, consentRegions (ISO 3166-2 codes where a wait site holds Google's tags back; unset means everywhere). Replaces the whole stored config: start from the site's capture in list_sites and change only what you mean to. Changing consent settings means the operator must re-paste the site's snippet.
`primary`	No	true makes this the primary website.

Output Schema

Name	Required	Description	Default
`appUrl`	Yes
`siteId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 29, 2026

changedInput schema / properties / capture / description

Previous value: -"Lead-capture config: capture.kind selector|hubspot, honeypotField, gtmContainerId, cookiebotId, consentMode."New value: +"Lead-capture config: capture.kind selector|hubspot, honeypotField, gtmContainerId, cookiebotId, consentMode, consentRegions (ISO 3166-2 codes where a wait site holds Google's tags back; unset means everywhere). Replaces the whole stored config: start from the site's capture in list_sites and change only what you mean to. Changing consent settings means the operator must re-paste the site's snippet."

First observedOct 1, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnly=false, destructive=false and idempotent=true, but the description adds the key side effect none of them express: changing a hostname clears the AI readiness score and site audits. It also flags that edits must be scoped by siteId. It doesn't mention permission requirements, and the snippet re-paste requirement lives only in the capture param schema, so it isn't fully exhaustive.

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 short sentences: purpose, edit switch, destructive side effect plus related tools. Nothing is padded and the highest-risk fact (hostname change wipes audits) is surfaced rather than buried.

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 mutation tool with a rich nested schema, full annotations and an output schema, the description covers the operation, the add/edit discriminator, the destructive side effect and sibling pointers. An agent has everything needed to call it correctly without further inference.

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 description coverage is 100%, so every parameter including the nested capture object is already documented in detail (hostname format, add-vs-edit meaning of siteId, replacement semantics). The description restates the field list and the siteId edit rule but adds no syntax or format detail beyond the schema, so baseline 3 applies.

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 pair and resource ("Adds or edits a website") and enumerates the fields under control (hostname, name, primary flag, lead-capture settings). It also names the neighbouring tools (list_sites, delete_site), so an agent can tell it apart from siblings without opening a 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?

"Pass siteId to edit" gives the exact add-vs-edit discriminator, which is the central usage decision for this tool. The "Related: list_sites, delete_site" line points at alternatives but doesn't state the conditions that would send the agent to them, so it stops just short of an explicit when/when-not rule set.

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

All Mark tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?