Transcript Phrase Trend
GetTranscriptPhraseTrendCount how often a word or phrase comes up on a company's last earnings calls, oldest first: mentions per call, the rate per 10,000 words, the split between prepared remarks and Q&A where the call states its hand-off to questions, and one or two short quotes. Whole-word and case-insensitive, so "AI" never matches "said"; spellings that differ by a hyphen or a join count together ("copilot" also finds "co-pilot"), and the calls list which spelling they used. A call with no transcript text, or one in Chinese, Japanese or Korean, is flagged, never zero. Use it to follow a product, risk or initiative across quarters.
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": {
"ticker": "<ticker>",
"phrase": "<phrase>"
},
"name": "GetTranscriptPhraseTrend"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| calls | No | Number of most recent earnings calls to read (default 8, max 12; values outside 1-12 are clamped) | |
| phrase | Yes | Word or phrase to count, 2-80 characters after trimming (e.g. "tariffs", "sovereign AI"). Matched as whole words, ignoring case. A space or hyphen between words matches any whitespace, a hyphen or no gap ("co-pilot" finds "co pilot" and "copilot"), and a hyphen may split a word between two letters ("copilot" finds "co-pilot"); numbers never join, so "2025" never counts "20-25". | |
| ticker | Yes | Company ticker symbol (e.g., AAPL, MSFT), or MIC:TICKER (e.g., XPAR:AIR) for a listing outside the US. |