Skip to main content
Glama
Sign In

EdgarStack

by com.edgarstack
OverviewDiscussionsAdmin

Build an initiation report: Excel model plus report pack

build_research_report
Read-onlyIdempotent

One call produces both deliverables of a sell-side initiation for a US-listed operating company:

  1. The Excel model (same builder as build_financial_model) with a Target Price tab: EV/EBIT valuation with Bear/Base/Bull multiples, a blended DCF + multiple 12-month target, upside and rating, sensitivity, and the return profile. Returned as a download link.

  2. A report pack for you to write a 3-page initiation note: key metrics table, valuation outputs read from the evaluated workbook, chart data (share price, stock vs sector ETF, margin trend), SEC filing evidence with citations (business, segments, guidance, risk-factor changes, ownership, insiders), the report outline, writing rules, consistency checks and caveats. Write the note strictly from the pack and give the user both the note and the model link. Quote the model's numbers exactly; address every caveat (the generated DCF uses placeholder WACC inputs, and the Base multiple is a neutral default unless the user gives one). Before calling, if the user hasn't said, ask for 2-5 peers and whether they want a DCF weight other than 30%; proceed with defaults if they decline. Not for banks or insurers (use build_report_pack). Not investment 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": "build_research_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
peersNoUp to five comparable tickers for the peer section
tickerYesUS ticker symbol, e.g. CROX
dcfWeightNoWeight of the DCF in the blended target (default 0.3; the rest is EV/EBIT)

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say read-only/open-world/idempotent; the description adds substantive behavior the agent could not infer: two artifacts returned, the model as a download link, and two explicit caveats (placeholder WACC inputs, neutral default Base multiple) that must be disclosed to the user. That is exactly the value-add beyond annotations.

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?

Long but well structured: a numbered list of the two deliverables, then a paragraph of operating instructions, then prerequisites/exclusions. Nearly every sentence carries information; the "quote the model's numbers exactly" instruction is behaviorally load-bearing rather than filler.

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?

With no output schema, the description carries the full burden of describing returns, and it does: workbook contents, the pack's sections (metrics, valuation outputs, chart data, SEC citations, outline, rules, checks), and the download link. Prerequisites, exclusions, and caveats are all present, so an agent can call this correctly in one shot.

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 baseline is 3, but the description adds meaning beyond the schema: peers should be 2-5 (a minimum the schema's maxItems:5 does not encode) and dcfWeight is only solicited if the user has an opinion, otherwise 0.3 stands. Marginal gain over a well-documented schema, not transformative.

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 and two named deliverables (Excel model with a Target Price tab, plus a report pack for a 3-page initiation note), and explicitly distinguishes itself from build_financial_model (same builder) and build_report_pack (for banks/insurers). An agent can tell exactly what it produces versus its closest siblings.

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 explicit when-not guidance ("Not for banks or insurers (use build_report_pack)") and a pre-call procedure: ask for 2-5 peers and any non-default DCF weight, then proceed with defaults if declined. This is the rare definition that routes both to alternatives and to user interaction.

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