jwatte.com website tools

Get a run link for a site

get_audit_link

Read-onlyIdempotent

Creates a browser run link for a catalog tool that supports website addresses. Opening the link fills in the address and starts that tool, which may fetch the target through the site hosting function and configured proxies. The MCP call itself never fetches or audits the target and returns no audit findings. Accepts public HTTP or HTTPS addresses only; rejects private addresses, internal names, credentials and non-standard ports.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "https://example.com",
      "tool": "mega-analyzer"
    },
    "name": "get_audit_link"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes	The public page or site to audit. A bare host name uses HTTPS.
`tool`	Yes	Tool slug, e.g. "mega-analyzer", "wcag-accessibility-audit", "agent-ready-audit".

Output Schema

Name	Required	Description	Default
`note`	Yes
`tool`	Yes
`target`	Yes
`autorun`	Yes
`run_url`	Yes
`fetched_by_server`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 8, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well past the annotations by explaining the downstream consequence: opening the link fills in the address and starts the tool, which may fetch the target via the site hosting function and configured proxies, while the MCP call itself never fetches or audits anything. It also discloses input rejection rules, which the readOnly/openWorld/idempotent hints alone would not convey.

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?

Four sentences, front-loaded with the action, then behavior, then constraints. Every sentence carries information, though the proxy/hosting clause is dense and slightly jargon-heavy for a definition that could state the fetch behavior more plainly.

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, yet the description still preempts the most likely agent misread by stating no audit findings are returned. Input constraints, side effects of opening the link, and the non-fetching nature of the call are all covered for a two-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns an extra point by adding validation semantics for the url parameter that the schema lacks: public HTTP/HTTPS only, private addresses, internal names, credentials and non-standard ports are rejected. It also constrains the tool slug to catalog entries that support website addresses.

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: "Creates a browser run link for a catalog tool that supports website addresses." It also draws the crucial boundary against sibling catalog tools (list_audit_tools, find_tool) by clarifying that this tool only produces a link and does not run an audit.

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?

The description implies when the tool is appropriate (you have a public address and a tool slug) but never explicitly names an alternative or an exclusion condition, such as when to use find_tool or list_audit_tools instead. Usage is inferable rather than stated.

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

All jwatte.com website tools 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?