Skip to main content
Glama
Sign In

EdgarStack

by com.edgarstack
OverviewDiscussionsAdmin

Build a cited evidence pack for an analyst-style report

build_report_pack
Read-onlyIdempotent

One call returns everything needed to write an analyst-style report from SEC filings: the relevant data sections, SEC filing citations for each section, writing rules and a report outline. You (the model) then write the report from the pack only. Report types:

  • "earnings_recap" (~12k tokens): latest quarterly XBRL results, 8-K earnings release (Ex-99.1), TTM ratios, segments, guidance language, changed MD&A/Risk Factors passages, insider trades.

  • "tenk_red_flags" (~18k tokens): earnings-quality indicators, growth anomalies, five-year ratios, off-balance-sheet items, risk-factor changes, revised XBRL facts, auditor-change/restatement 8-Ks, balance-sheet tie-out.

  • "initiation" (~25k tokens): business description, five-year financials and ratios, segments, valuation, peers, capital allocation, guidance track record, risk changes, ownership, insiders. Packs stay under a hard token budget; lower-priority sections are trimmed first and listed in trimmedSections, and failed sections are listed in unavailableSections. If the user's request doesn't clearly map to one report type (e.g. "write me a report on X"), ask which of the three they want, with a one-line description of each, rather than guessing. For "initiation", if the user named no peers, ask for 2–5 comparable companies (suggest a few) before calling; peers are optional if they decline. Text sections cover US 10-K/10-Q filers. 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>",
      "reportType": "<reportType>"
    },
    "name": "build_report_pack"
  }
}

Input Schema

NameRequiredDescriptionDefault
peersNoinitiation only: up to five comparable tickers
tickerYesUS ticker symbol, e.g. AAPL
reportTypeYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: approximate token cost per report type, a hard token budget with lower-priority sections trimmed (listed in trimmedSections), failed sections surfaced in unavailableSections, and a coverage limit to US 10-K/10-Q filers. That tells the agent what it may not get back and why.

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 core contract and the ask-don't-guess rule are front-loaded, and the per-report-type bullets are scannable rather than prose. The three content lists are long, but each item is a real signal about what the pack contains, so the length is largely justified for a high-stakes, high-token call.

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 return contract itself: section types per report, the trimmedSections and unavailableSections signalling fields, and token budgets. For a three-parameter, high-cost orchestration tool, an agent has everything needed to call it and interpret the response.

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 67%, and the description compensates by defining each reportType value as a concrete content bundle with token cost, which the bare enum cannot convey. The peers constraint is restated from the schema rather than extended, and ticker gains no new meaning, so it falls short of full coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence states a concrete verb and artifact: one call returns data sections, SEC citations, writing rules and an outline for an analyst-style report, and it explicitly says the model writes the prose from the pack. That clearly separates it from a report-generating tool, though no sibling (e.g. build_research_report) is named as an alternative.

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?

It specifies exactly which of three report types to pick and what each contains, tells the agent to ask the user rather than guess when a request is ambiguous, and requires asking for 2-5 peers before 'initiation' calls (optional if declined). This is explicit when-to-use, when-to-ask, and prerequisite guidance.

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