Skip to main content
Glama

Earnings Call Transcript

GetEarningsCallTranscript
Read-only

Get the speaker-labelled transcript of a company's earnings call for a fiscal quarter — every speaker turn in order, attributed to the real person (executive or sell-side analyst) with their role at the time. Identities appear only when the resolution is trusted (auto-resolved or human-reviewed); unverified voices show as a role label (e.g. Operator) or a neutral speaker number. While a call is being recorded live, and until its speaker-labelled transcript is ready, the tool returns the preliminary live text instead: numbered machine-transcribed lines without speaker labels, growing every ~20 seconds. Pass after= and run= to receive only the lines spoken since. The answer says when no transcript exists yet. In chat apps that show interactive cards, the answer also plays the call's recording beside the synced transcript, so a request to hear or listen to a call is answered here.

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>"
    },
    "name": "GetEarningsCallTranscript"
  }
}

Input Schema

NameRequiredDescriptionDefault
runNoLive text only: the run value from the previous live answer; a different run means the recording restarted and the answer carries the full text again
afterNoLive text only: the highest line number already received (default -1, the whole text so far); the answer then carries only the lines after it
limitNoMaximum number of speaker turns to return (default 50, max 200; values outside 1-200 are clamped)
offsetNoNumber of leading speaker turns to skip, for paging through calls longer than the 200-turn cap (default 0)
tickerYesCompany ticker symbol (e.g., AAPL, MSFT), or MIC:TICKER (e.g., XPAR:AIR) for a listing outside the US.
fiscalYearNoCompany fiscal year. Omit both period fields for the latest call; year alone selects the latest call in that fiscal year.
fiscalQuarterNoCompany fiscal quarter, 1-4. Quarter alone selects the latest matching quarter across fiscal years; provide both fields for an exact period.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / after
      Added value: +{
      +  "default": -1,
      +  "description": "Live text only: the highest line number already received (default -1, the whole text so far); the answer then carries only the lines after it",
      +  "type": "integer"
      +}
    • addedInput schema / properties / run
      Added value: +{
      +  "default": null,
      +  "description": "Live text only: the run value from the previous live answer; a different run means the recording restarted and the answer carries the full text again",
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / ticker / description
      Previous value: -"Company ticker symbol (e.g., AAPL, MSFT)"New value: +"Company ticker symbol (e.g., AAPL, MSFT), or MIC:TICKER (e.g., XPAR:AIR) for a listing outside the US."
  3. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare a safe read; the description adds substantial context beyond them: the live-text fallback state, the ~20-second growth cadence, the incremental polling protocol with after/run, and the trust model for speaker identity resolution. It also discloses the empty-transcript outcome, which an agent needs to interpret a null-ish response.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The primary purpose is front-loaded in the first clause, followed by edge cases in a sensible order: normal case, live fallback, no-transcript case, card behavior. Dense but mostly earned; the final sentence about interactive cards and playback is the least essential to correct invocation.

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 seven-parameter read tool with no output schema, the description covers the normal path, the live/preliminary path with polling semantics, the missing-transcript outcome, and paging through long calls. An agent can call it correctly and interpret the major response variants without further guidance.

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 schema already defines all seven parameters; the description nevertheless adds operational meaning to the live-only parameters by saying to pass after=<the last line number you hold> and run=<the run it reported> to get only newer lines — a usage pattern the schema wording only implies. It adds nothing extra about limit/offset paging or ticker formats, which the schema covers well.

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 names a specific verb and resource — the speaker-labelled transcript of a company's earnings call for a fiscal quarter — and pins down what that means (every speaker turn in order, attributed to a real person with role, or a fallback label when verification fails). That level of specificity lets an agent distinguish this from other transcript/event tools without opening any schema.

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 states the conditions that change behavior (live recording in progress returns preliminary numbered lines; no transcript yet returns that fact) and explicitly routes a 'hear or listen to the call' request to this tool in card-capable chat apps. It stops short of naming sibling alternatives such as event transcripts or theme tools, so there is no explicit when-not-this-tool exclusion.

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.