Skip to main content
Glama

Finnhub (Unofficial)

Get Earnings Surprises

get_earnings_surprises
Read-onlyIdempotent

EPS actual vs analyst (consensus) estimate, beat or miss, for a company's recent quarters, the "earnings surprise" history. Returns per quarter: fiscal period, EPS actual, EPS estimate, surprise amount and percent. Revenue is NOT included (Finnhub's earnings-surprise data is EPS-only); for revenue estimates on upcoming quarters, see get_earnings_calendar. Example: get_earnings_surprises({ symbol: "MSFT", limit: 4 })

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "limit": 4,
      "symbol": "MSFT"
    },
    "name": "get_earnings_surprises"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoNumber of most-recent quarters to return (default 4, max 20)
symbolYesStock ticker symbol, e.g. "AAPL", "MSFT", "TSLA"
_apiKeyYesFinnhub API key (get one free at finnhub.io)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so safety is covered, but the description adds real context: the data is EPS-only by vendor limitation, and it enumerates the per-quarter payload. It does not mention rate limits or whether history depth beyond 'recent quarters' is capped (the schema's max 20 covers that only implicitly).

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?

Front-loads the definition, then the return shape, then the exclusion and alternative, ending with a compact example. Dense and largely waste-free, though the quoted phrase 'earnings surprise' and the example are somewhat redundant given 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?

No output schema exists, so the description carries the return-shape burden and does so by listing every per-quarter field. Combined with annotations and full schema coverage, an agent has everything needed to call it correctly and to know what will come back.

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 description coverage is 100%, so symbol, limit and _apiKey are already documented, and the description largely restates them. It contributes marginally by framing results as 'recent quarters', which clarifies the ordering semantics of limit, but adds no format or constraint detail beyond the schema.

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?

Names a specific measurement (EPS actual vs analyst consensus estimate, beat/miss) over a specific scope (a company's recent quarters), and explicitly distinguishes itself from get_earnings_calendar for revenue estimates. The per-quarter return fields (fiscal period, EPS actual, EPS estimate, surprise amount and percent) further pin down what the tool produces.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit boundary ('Revenue is NOT included') and routes the agent to the correct sibling for the adjacent need ('for revenue estimates on upcoming quarters, see get_earnings_calendar'). The worked example anchors the typical invocation shape.

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.