Cursor
Grok Bot
Grok
MuseTitle100/100
Check a link for phishing
The title clearly communicates the tool’s action and subject. Keep it concise.
Description94/100
Check a URL for phishing signals: brand lookalike domains, suspicious TLDs, raw IP addresses, plain HTTP, @-tricks, encoded hostnames, punycode, and tokens in the query string. Looks at the URL only; it does not visit it. Returns riskLevel (safe, caution, danger) and the signals found.
The description explains the capability, when to use it, and what to expect.
Inputs100/100
Input documentation gives an agent enough context to populate the arguments.
url
The link the person received or is about to open, copied as it appears, query string included. Use this before saying a link is safe.
Clear enough to supply this argument.
Annotations100/100
All four behavior hints are declared.
{
"title": "Check a link for phishing",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}Output schema84/100
Align the output schema with the tool’s documented result.
View output schema
{
"type": "object",
"required": [
"safe",
"riskLevel",
"signals"
],
"properties": {
"safe": {
"type": "boolean",
"description": "True when no signals were found; it is not a guarantee the site is safe"
},
"signals": {
"type": "array",
"items": {
"type": "object",
"required": [
"severity",
"title",
"desc"
],
"properties": {
"desc": {
"type": "string",
"description": "One-sentence explanation for the person"
},
"title": {
"type": "string",
"description": "Short name of the finding"
},
"severity": {
"enum": [
"red",
"amber"
],
"type": "string"
}
}
},
"description": "Warning signs found in the URL; red ones set riskLevel to danger"
},
"riskLevel": {
"enum": [
"safe",
"caution",
"danger"
],
"type": "string"
}
}
}