Skip to main content
Glama
Sign In

EdgarStack

by com.edgarstack
OverviewDiscussionsAdmin

Compare sections across SEC filings

diff_filing_sections
Read-onlyIdempotent

Compare what changed between a company's 10-K or 10-Q filings. All views return source-linked added, removed and modified passages with SEC filing dates and accession numbers. Four views:

  • view="sentences" (default): full sentence-level diff of ONE Item (itemNumber, e.g. '1A' Risk Factors, '7' MD&A for a 10-K, '2' MD&A for a 10-Q) between two filings — the latest two unless you pass oldAccessionNumber/newAccessionNumber. Covers every sentence. Only pass oldText/newText for text from elsewhere.

  • view="brief": a prioritized brief across up to 4 sections (itemNumbers; defaults to 1A and 7 for 10-K, or 1A and 2 for 10-Q) of the latest two filings, ordered by a deterministic keyword and change-type heuristic; maxChanges 1–30, default 12. Reports extraction failures per section.

  • view="risk_topics": Item 1A changes grouped by a fixed risk keyword taxonomy (passages can sit in several categories or stay unclassified).

  • view="mda_topics": MD&A changes grouped by fixed topics — revenue/demand, margins, liquidity, capital, accounting estimates, trends; unclassified passages stay visible. Ordering and categories are search aids; they do not establish materiality or causality. Not financial or legal advice.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "diff_filing_sections"
  }
}

Input Schema

NameRequiredDescriptionDefault
viewNosentences
tickerNoCompany ticker, e.g. TSLA. Required except when diffing raw oldText/newText.
newTextNoview=sentences: raw section text from the later filing (only if not using ticker + itemNumber)
oldTextNoview=sentences: raw section text from the earlier filing (only if not using ticker + itemNumber)
formTypeNo10-K
itemNumberNoview=sentences: Item to compare, e.g. '1A' or '7' for a 10-K, '2' for 10-Q MD&A
maxChangesNoview=brief: maximum changed passages returned
itemNumbersNoview=brief: sections to compare; omit for the defaults
newAccessionNumberNoview=sentences: later filing. Omit to use the latest.
oldAccessionNumberNoview=sentences: earlier filing (from list_recent_filings). Omit to use the second-latest.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive and open-world, so the bar is lower, but the description still adds real behavior: all views return source-linked added/removed/modified passages with SEC filing dates and accession numbers, brief reports extraction failures per section, unclassified passages stay visible, and the ordering/categories are explicitly non-materiality heuristics with a not-advice caveat.

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 one-sentence summary before the four-view list, and each bullet carries distinct operational content. It runs long for a description, with some density that could be trimmed, but no bullet is filler given ten parameters and four modes.

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?

There is no output schema, yet the description covers what comes back, per-section failure reporting, and the interpretive limits of the ordering. What is missing is failure behavior when a ticker, item, or accession number is invalid, and whether results are size-limited beyond maxChanges.

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 80%, so the baseline is 3; the description earns an extra point by tying parameters to modes and, importantly, spelling out the brief defaults (1A and 7 for 10-K, 1A and 2 for 10-Q) that the schema only alludes to, plus the latest-two-filings default for the accession numbers. formType and ticker semantics are left largely to 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?

States a specific verb and resource (compare changes between a company's 10-K or 10-Q filings) and then enumerates the four distinct views with what each produces. An agent can tell exactly what the tool does and which mode it needs without opening the schema.

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 per-view selection guidance (sentences for a full diff of one Item, brief for up to 4 sections, risk_topics and mda_topics for taxonomy-grouped views), states the defaults each view falls back to, and names the condition for using raw oldText/newText instead of ticker+itemNumber. It also points to list_recent_filings as the source of accession numbers.

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