Skip to main content
Glama
Sign In

EdgarStack

by com.edgarstack
OverviewDiscussionsAdmin

Get standardized financial statement data, trends, or revisions

get_financials
Read-onlyIdempotent

Pull standardized financial line items for a US-listed company from SEC XBRL filings. Available metrics: revenue, grossProfit, operatingIncome, netIncome, epsBasic, epsDiluted, totalAssets, currentAssets, totalLiabilities, currentLiabilities, longTermDebt, totalEquity, cashAndEquivalents, operatingCashFlow, capex, rdExpense, sharesOutstanding, dividendsPerShare, dividendsPaid, stockBasedCompensation, deferredRevenue, goodwill, intangibleAssets, depreciationAmortization, costOfGoodsSold, sellingGeneralAndAdministrative, interestExpense, otherNonoperatingIncomeExpense, pretaxIncome, incomeTaxExpense, liabilitiesAndEquity, assetImpairment, shortTermInvestments, weightedAverageDilutedShares, shareRepurchases, accountsReceivable, inventory, accountsPayable, propertyPlantEquipment, investingCashFlow, financingCashFlow, grossInterestIncome, netInterestIncome, noninterestIncome. Three views:

  • view="values" (default): values per period with the XBRL tag used and source filing accession numbers. period="ttm" returns latest FY + current YTD - prior-year comparable YTD for flows (or FY when the latest fact is year-end), and latest instant values for balance-sheet metrics. fiscalYear is derived from the fact's periodEnd; sourceFilingFiscalYear preserves SEC filing metadata. limit 1–40, default 8.

  • view="trends": changes, guarded growth rates and filing provenance for up to 8 metrics (default revenue, operatingIncome, netIncome, operatingCashFlow, capex). Quarterly mode compares adjacent reported quarters and matches year-over-year quarters by actual period end; missing periods are not imputed. Annual mode also returns endpoint CAGR. Annual or quarterly only; limit 2–10, default 8. Historical analysis, not a forecast.

  • view="revisions": values the company later reported differently for the same XBRL tag and exact period, with both filing dates and accession numbers (up to 6 metrics; defaults to revenue, net income, assets, operating cash flow). Annual or quarterly only; limit 1–50 changed facts per metric, default 20. A difference can reflect an amendment, reclassification, or updated comparative and does not alone establish a formal restatement. Not financial advice.

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": "get_financials"
  }
}

Input Schema

NameRequiredDescriptionDefault
viewNovalues = reported numbers; trends = growth and CAGR; revisions = later-changed reported factsvalues
limitNovalues: periods per metric (1–40, default 8); trends: observations per metric (2–10, default 8); revisions: changed facts per metric (1–50, default 20)
periodNoTTM is available for view=values only.annual
tickerYes
metricsNoSubset of available metrics; omit for all (values) or the view's defaults (trends, revisions)

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive, open-world access, and the description layers on substantive behavior: the exact TTM derivation formula, that missing periods are not imputed, that annual trends add endpoint CAGR, that fiscalYear is derived from periodEnd while sourceFilingFiscalYear preserves SEC metadata, and the interpretive limits of revisions. This is well beyond what the annotations convey.

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-loaded with purpose then structured as three bulleted view modes, with no filler sentences. The 40-item metric enumeration is bulky but earns its place by defining the legal values of the metrics array; a compact pointer to the schema could have trimmed it further.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates by naming the return payload per view (XBRL tag, accession numbers, filing dates, growth rates, CAGR). Given five parameters and three modes, an agent has enough to call it correctly, though the shape of a returned record is described only loosely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 80% schema coverage, the schema already documents view/limit/period/metrics, yet the description adds per-view limit ranges and defaults (1–40/8, 2–10/8, 1–50/20), the restriction that TTM is values-only, per-view metric defaults for trends and revisions, and the full enumeration of legal values for the metrics array. That is meaningfully more than the schema supplies.

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?

Opens with a specific verb+resource ("Pull standardized financial line items") and constrains the universe to US-listed companies from SEC XBRL filings, then enumerates the three views. An agent can distinguish this raw-fact retrieval tool from siblings like compute_ratios or build_financial_model 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?

Each view carries its own usage context: values for reported numbers, trends for "historical analysis, not a forecast," revisions for later-changed facts with an explicit caveat that a difference does not alone establish a restatement. It does not name sibling tools or say when to prefer compute_ratios/analyze_earnings_quality over raw facts, so it falls short of the explicit-alternatives bar.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All EdgarStack toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources