Cursor
Grok Bot
Grok
MuseTitle100/100
Web search
The title clearly communicates the tool’s action and subject. Keep it concise.
Description90/100
Search the live public web when the user needs current information, sources, or research. Returns citable results with id, title, URL, and text. Each result includes a URL that can be read in full.
The description explains the capability, when to use it, and what to expect.
Inputs95/100
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
query
Short, focused search query
Clear enough to supply this argument.
max_results
How many sources the answer needs; a handful suits most questions, more suits a broad survey
Clear enough to supply this argument.
search_service
Search engine to use; choose one only when it matches the user's source intent
Clear enough to supply this argument.
page
Which page of results to fetch when the first page was not enough; only bing, bingcn, and grokipedia paginate, other engines ignore it
Clear enough to supply this argument.
crawl_results
How many top results to also read in full, so their text holds the whole page instead of a snippet. Each successful page retrieval adds 1 credit to the base 1-credit search request
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
include_sites
Domains to include when the user explicitly scopes the search
Clear enough to supply this argument.
exclude_sites
Domains to exclude from the search
Clear enough to supply this argument.
time_range
Restrict results to those published recently, for time-sensitive questions; leave unset for evergreen topics
Clear enough to supply this argument.
Annotations100/100
All four behavior hints are declared.
{
"title": "Web search",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}Output schema91/100
The output schema explains the structured result.
View output schema
{
"type": "object",
"required": [
"results"
],
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"title",
"url"
],
"properties": {
"id": {
"type": "string",
"description": "Stable identifier for this result; for web results this is the canonical URL"
},
"url": {
"type": "string",
"format": "uri",
"description": "Canonical URL that clients can cite and users can open"
},
"text": {
"type": "string",
"description": "Result snippet or extracted page text when available"
},
"title": {
"type": "string",
"description": "Human-readable result title"
},
"metadata": {
"type": "object",
"description": "Additional source metadata",
"additionalProperties": true
}
}
},
"description": "Matching sources, most relevant first; read any url in full with crawl"
}
}
}