Skip to main content
Glama

isup.tools — is it down?

Check if a website is down

check_site
Read-onlyIdempotent

Check if a website is up or down right now. Use it when someone asks whether a site is down, or if it is just them. Makes one request to the site and returns a verdict sentence, the status (UP, DOWN or NOT CHECKABLE), the HTTP code, the time taken, and the real place the check ran from. The check runs near the machine that calls this tool, which may not be near the end user. The site's content is never read.

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 domain or full URL to check, for example example.com or https://example.com/status. A bare domain is tried over https first.

Output Schema

NameRequiredDescriptionDefault
reasonYesOne line on what happened.
statusYesUP: answered below HTTP 400. DOWN: answered 400 or higher (except 401, 403, 429), or no answer. NOT CHECKABLE: isup cannot reach this port or address (httpCode null), or the site answered 401, 403 or 429 and refuses automated checks; says nothing about whether the site works for people.
targetYesThe last URL checked, after any redirects.
verdictYesThe verdict sentence, for example "It's just you. example.com is up."
finalUrlYesThe last URL requested, after any redirects, or null when no request was sent.
httpCodeYesHTTP status code of the last answer, or null when there was no answer.
checkedAtYesWhen the check ran (UTC).
latencyMsYesTime the whole check took, in milliseconds, or null when no request was sent (unsupported port).
redirectsYesEvery redirect answer, in order: the URL requested and the 3xx code it answered. Empty when there were no redirects. A redirect the safety rules refused is not listed (reason says it was not followed). URLs longer than 300 characters are cut and end with …
resultUrlYesHTML page for this target. Opening it runs a new check.
checkedFromYesThe real place the check ran from: a city, a raw location code when the city is not known, or "Location unavailable". Never guessed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, but the description adds genuinely new operational context: exactly one request is made, the possible status values (UP, DOWN, NOT CHECKABLE), the returned fields, and that the check originates near the calling machine rather than the end user. That last point is a meaningful caveat an agent would otherwise get wrong.

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?

The purpose is stated first, usage second, return shape third, and caveats last. Every sentence carries distinct information, including the non-obvious 'content is never read' assurance and the location caveat, with no redundant restatement of the title.

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 one-parameter read tool, the description covers purpose, trigger, return shape, and the two behavioral caveats that matter (probe origin and content non-reading). Although an output schema exists and would have carried the return values, the description's summary of them is consistent and adds clarity rather than redundancy.

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 100%, and the schema itself explains that a bare domain is tried over https first, so the description is not required to carry parameter meaning. The description adds no format or syntax detail beyond the schema, so it sits at the baseline for a well-documented single parameter.

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 and resource plus a temporal scope: 'Check if a website is up or down right now.' An agent immediately knows this is a live reachability probe rather than a monitoring or history tool.

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?

It gives an explicit usage trigger: 'Use it when someone asks whether a site is down, or if it is just them.' That covers the common intent well. There are no sibling tools to route away from, so the absence of exclusions is not a real gap.

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.

Resources