Skip to main content
Glama

beatandraise.com SEC Filings

List Filings

get_filings
Read-onlyIdempotent

Query SEC filings by form type, date range, CIK and/or 8-K item.

Returns filings newest first. Each filing's content_object lists its documents (sequence 1 is the primary); read one with get_document(cik, accession_number, filename). Cite beatandraise_base_url + filename; the filing's source has a ready-made citation. 8-Ks carry their items ("2.02 Results of Operations..."). R*.htm files are XBRL table pages (list_filing_tables names them).

An 8-K carries a headline when its press release has one: found by rules, so use it to choose which 8-K to read, not as a quotation (verify_quote first). No headline says nothing about the filing. An 8-K with only Item 9.01 and no headline files exhibits only (exhibits_only lists them) and is rarely news.

Args: form: SEC form type (e.g. "10-K", "10-Q", "8-K", "4", "13F-HR", "S-1"), or several comma-separated in one call (up to 20), e.g. "N-CSR,N-CSRS,N-CSR/A,N-CSRS/A" or "10-K,10-K/A". Amendments are their own form types, so name them to include them. cik: Company CIK (e.g. "0000320193" or "320193") from_date: Start date inclusive (YYYY-MM-DD). Without cik, defaults to 30 days before to_date (or today); pass it to reach older filings. to_date: End date inclusive (YYYY-MM-DD) limit: Max results (1-100, default 100; at most 25 with include_item_text). For more, page with offset offset: Pagination offset item: Only 8-Ks reporting this item, by its number as the 8-K header states it, e.g. "5.02" (departure or election of directors or officers, officers' pay), "1.01" (material agreement), "2.01" (acquisition or disposal), "4.01" (auditor change), "5.07" (shareholder vote); several comma-separated match any ("1.01,2.01"). Defaults form to "8-K,8-K/A". Numbered since 2004-08-23. Use it instead of reading 8-Ks one by one. include_item_text: With item, also return each filing's text of that item (item_texts, with a highlight_url), so a screen across companies is one call: whether a 5.02 is a director, a CEO or a pay plan is in the text. item_text: Items whose text to return with each 10-K, 10-Q or 8-K, by number or name, up to 5 comma-separated ("MD&A", "1A", "Risk Factors", "5.02"). With form="10-Q" and a cik, "MD&A" gives the last several MD&As in one call. item_text_chars: Characters per Item, 1,000-100,000 (default 10,000); a page carries at most 500,000, so limit is lowered to fit.

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": "get_filings"
  }
}

Input Schema

NameRequiredDescriptionDefault
cikNo
formNo
itemNo
limitNo
offsetNo
to_dateNo
from_dateNo
item_textNo
item_text_charsNo
include_item_textNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare a safe, idempotent, read-only, open-world read, so the description's added context is genuinely extra: result ordering (newest first), the paging constraint that limit is lowered to fit a 500,000-char page, and the caveat that rule-derived 8-K headlines are for selection, not quotation. The exhibits-only signal and the 'no headline says nothing' warning are behavior an agent could not infer from the schema.

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 purpose, then return/reading behavior, then a structured Args block with zero filler sentences. It is long, and the headline/exhibits paragraph is dense prose that could be tightened, but each element carries operational value rather than restating the schema.

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?

For a 10-parameter, zero-schema-documentation, high-fan-out query tool, nothing an agent needs to call it correctly is missing: format of results, pagination path, item semantics, and the follow-up tools (get_document, list_filing_tables, verify_quote). An output schema exists, yet the description still explains content_object and item_texts defaults, which is a bonus rather than a gap.

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?

Schema description coverage is 0%, so the description carries the full burden, and it documents all ten parameters with examples and bounds: comma-separated form lists up to 20 ('N-CSR,N-CSRS,N-CSR/A'), CIK formats, inclusive date semantics, limit 1-100 dropping to 25 with include_item_text, offset paging, item numbers with plain-English meanings, and item_text_chars 1,000-100,000.

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 first line states a specific verb and resource plus the exact filter axes: 'Query SEC filings by form type, date range, CIK and/or 8-K item.' The scope is narrow and operational, so an agent can distinguish this from general document-search siblings 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 concrete when-to-use routing: use `item` 'instead of reading 8-Ks one by one', `include_item_text` when screening across companies, `item_text` with form=10-Q to get several MD&As in one call. It also states defaults and precedents (from_date defaults to 30 days back without cik; `item` defaults form to 8-K,8-K/A) and warns that amendments are separate form types.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources