Skip to main content
Glama

Check a website

check_site

Starts NightMarquee's AI-look check of a public website and returns a job. Read the result with get_job, which asks you to come back in a few seconds. The result page is unlisted: it is not shown on the public board, and anyone with the link can read it. Set publish to true only when the user asks for a public result. A check of the same address from the last day is reused. Each account can run five checks an hour and twenty a day. Needs a connected account.

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": {
      "url": "<url>"
    },
    "name": "check_site"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe public website address to check, for example https://example.com.
publishNoList the result publicly. Leave it false unless the user asks for a public result.

Output Schema

NameRequiredDescriptionDefault
idYes
kindYes
errorYes
statusYes
retryAfterSecondsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only declare openWorldHint=true and destructiveHint=false, but the description adds the operation's real behavioral profile: it is asynchronous and returns a job rather than a result, results are unlisted and readable by anyone with the link, identical checks within the last day are reused, and each account is capped at five per hour and twenty per day. That caching and rate-limit disclosure is exactly the kind of context an agent cannot get from structured fields.

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?

Seven short sentences, each carrying distinct information: purpose, follow-up routing, visibility semantics, publish guidance, deduplication, quotas, auth. The core purpose is front-loaded and nothing is padding.

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 not be described, and the description still covers the async/job lifecycle, auth requirement, rate limits, and result visibility. For a two-parameter, open-world tool, nothing an agent needs to call it correctly is missing.

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, but the description adds meaning the schema does not: it explains what the default unlisted state actually implies (not on the public board, yet link-readable by anyone), which is the consequence an agent must weigh before flipping publish. The rest largely restates the schema's own publish guidance rather than extending it.

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 — starts an AI-look check of a public website and returns a job. It also explicitly hands off the follow-up read to get_job, so an agent can distinguish the two tools without inspecting either schema.

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

Usage Guidelines5/5

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

Gives explicit when-to-use (call this to start a check, then poll with get_job) and an explicit when-not guard for the only optional parameter: set publish to true only when the user asks for a public result. It also names prerequisites (a connected account) and quotas, leaving little to inference.

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.