Mark

Run Site Audit

run_site_audit

Starts a new crawl and audit of a site, up to 50 pages. Results arrive in minutes; poll get_site_audit. If this refuses because the workspace is not set up, call get_setup_status and check its rows, including skipped ones. Related: get_site_audit, list_sites, save_site.

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": {
      "siteId": "<siteId>"
    },
    "name": "run_site_audit"
  }
}

Input Schema

Name	Required	Description	Default
`siteId`	Yes	Site id from list_sites.

Output Schema

Name	Required	Description
`audit`	Yes
`scope`	No	What the run checks.
`state`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 14, 2026

addedOutput schema / properties / scope

Added value: +{
+  "additionalProperties": false,
+  "description": "What the run checks.",
+  "properties": {
+    "summary": {
+      "description": "The same line the app shows beside the button.",
+      "type": "string"
+    },
+    "units": {
+      "description": "How many checks, pages or questions.",
+      "type": "number"
+    }
+  },
+  "required": [
+    "units",
+    "summary"
+  ],
+  "type": "object"
+}

First observedOct 1, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations cover mutation/safety (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true), and the description adds real value on top: asynchronous return, expected latency ('in minutes'), page cap, and the failure mode plus recovery tool. It does not say whether re-running creates a duplicate audit or consumes quota, which matters given non-idempotency.

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 short sentences, front-loaded with purpose and timing, then failure recovery, then related tools. The trailing 'Related:' list mostly repeats tools already named (get_site_audit) or easily inferred (list_sites, save_site), so it is marginally redundant.

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?

An output schema exists, so return values need no explanation, and the description still covers the async lifecycle, latency, scope cap, and the setup-failure recovery route. Nothing an agent needs to invoke this correctly is missing.

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?

Only one parameter, siteId, and the schema already documents it at 100% coverage ('Site id from list_sites'). The description adds no further semantics about the parameter, so this sits at the baseline where the schema does all the work.

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+resource ('Starts a new crawl and audit of a site') plus an explicit scope limit ('up to 50 pages'). The distinction from get_site_audit (which polls results) is made in the first sentence, so an agent can tell the two apart immediately.

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 clear lifecycle instruction ('Results arrive in minutes; poll get_site_audit') and a concrete fallback path when the call fails due to workspace setup. It stops short of saying when NOT to use this (e.g., site already has a recent audit, or needing >50 pages), which is the remaining gap.

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?