EdgarStack

Build a branded Excel financial model

build_financial_model

Read-onlyIdempotent

Generate a formula-driven five-year annual Excel workbook for a US-listed company: metric-specific SEC accession notes, Source Data, Standardized Data, editable assumptions, average-equity ROE, a historical working-capital view, a Segments tab (revenue and profit by business segment and revenue by region from the 10-K XBRL segment tables, with mix, growth, segment margins and a tie-out to reported revenue; omitted for companies that tag no segments), and Base/Upside/Downside forecasts with year-specific margin, tax, and share-count assumptions. When available, forecast working capital from DSO/DIO/DPO. The workbook includes a DCF with illustrative CAPM/WACC inputs, terminal-value sensitivity, a Dashboard, formula-driven Model Checks, and Audit Flags. Missing data displays as n/a; a generation-time formula scan is included. DCF assumptions are not market-verified. A Target Price tab blends the DCF with Bear/Base/Bull EV/EBIT multiples into a 12-month target, upside and rating; its WACC is a placeholder and its Base multiple a neutral default until the user sets them. Annual periods only (quarterly company facts have a structural Q4 gap). Ask whether the user wants the optional Valuation tab before setting includeValuation — it pulls a Tiingo price snapshot.

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": "build_financial_model"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Number of most recent annual periods to include
`ticker`	Yes
`includeSegments`	No	Add the Segments tab (business segment and regional breakdowns)
`includeValuation`	No	Add a Valuation tab (P/E, P/S, P/B, EV/Revenue, EV/EBITDA) from a live price snapshot

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint), yet the description adds substantial disclosure beyond them: missing data renders as n/a, a generation-time formula scan runs, DCF assumptions are not market-verified, WACC and Base multiple are placeholders, and the Segments tab is omitted when no segments are tagged. The one gap is that it never says what the caller receives (a file path, a download, a blob).

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

Conciseness3/5

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

The core purpose is front-loaded, but the first sentence is an extremely long run-on that crams every tab, caveat, and assumption into one breath. All the content is arguably useful, yet the lack of sentence breaks or grouping makes it harder to scan than it needs to be.

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?

For a complex generator with no output schema, the description covers scope, tab inventory, data-source caveats, placeholder assumptions, and parameter conditions thoroughly. The notable omission is the return artifact — whether the workbook is returned as a file, a URL, or saved server-side — which an agent needs before invoking.

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 75%, and the description still adds real meaning: includeSegments is conditional ('omitted for companies that tag no segments'), includeValuation triggers a live Tiingo price snapshot pull, and ticker is constrained to US-listed companies. Only limit is left slightly ambiguous, since the prose says 'five-year' while the schema permits 2–10 periods.

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 opens with a specific verb and resource — 'Generate a formula-driven five-year annual Excel workbook for a US-listed company' — and then enumerates the exact tabs produced. This is unmistakably distinct from siblings like build_report_pack or build_research_report, which are document builders rather than Excel model generators.

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 gives concrete usage context: 'Ask whether the user wants the optional Valuation tab before setting includeValuation', and a hard constraint that 'Annual periods only (quarterly company facts have a structural Q4 gap)'. It does not name alternatives for raw data retrieval (e.g. get_financials), so the routing guidance is clear but incomplete.

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

All EdgarStack tools Inspect

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

Need Help?