Skip to main content
Glama
Bosco Labs Data

Bosco Labs Data

Official

SEC insider trades (Form 4)

search_sec_insider_trades
Read-only

Find who is buying or selling a stock by searching SEC Form 4 insider trades by ticker, CIK, date, role, or code, including cluster buys and source filing links.

Instructions

US insider trades reported to the SEC on Form 4 (officers, directors, 10% owners), from today's filings back to 2006 (source: SEC EDGAR Form 4 XML and the SEC insider data sets). Use it for "who is buying/selling stock X", insider activity before an event, or market-wide insider buying (cluster buys).

Filter by tickers or CIKs (omit both for the whole market; a whole-market scan of many
days can take a minute or more, so prefer tickers). Filing date range: date_from/date_to,
or the last `lookback_days` days. Newest first.

Returns one row per transaction: filing_date, ticker, issuer_name, insider_name,
insider_roles, officer_title, transaction_date, transaction_code (P buy, S sell, ...),
shares, price, value_usd, shares_owned_after, plan_10b5_1 (pre-planned sale; unknown
before 2023-04), usable_from (first day a backtest may act on the row),
in_cluster and filing_url (the SEC filing; cite it).

Cost to the user: $0.0018 per transaction returned.

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": "search_sec_insider_trades"
  }
}

Input Schema

NameRequiredDescriptionDefault
ciksNo
clusterNoOnly trades in a cluster: 2+ directors/officers of one company trading the same way within 30 days, together >= $100,000
date_toNo
tickersNo
date_fromNo
max_resultsNoMax transactions to return (1-100).
insider_rolesNo
lookback_daysNoDays back when date_from is omitted; omit for the default (90 days for tickers/CIKs, 7 days for the whole market)
min_value_usdNoSkip smaller trades
transaction_codesNoForm 4 codes; omit for P (open-market purchase) and S (sale). Others: A award, M option exercise, F tax withholding, G gift.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.5

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations, it discloses the per-row cost ($0.0018 per transaction returned), the latency characteristics of a whole-market scan, ordering (newest first), the plan_10b5_1 data limitation (unknown before 2023-04), the usable_from backtest semantics, and that filing_url should be cited. That is far more than the annotations carry.

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 what the tool is and when to use it, then filters, then returns, then cost – a sensible order with no filler sentences. The long enumeration of return fields is dense but informative; the cost line would arguably be more useful earlier given it affects query design.

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, open-world, paid, read-only search tool with an output schema, the description covers source, coverage window, filter trade-offs, latency, pricing, row semantics, and data caveats. An agent has everything needed to choose parameters and interpret results without opening the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%, and the description compensates well for the core filters: tickers vs CIKs and the whole-market fallback, date_from/date_to vs lookback_days with its differing defaults per mode. However, min_value_usd, insider_roles, max_results and transaction_codes are not elaborated in the prose (codes are only glossed via the return-field explanation), leaving several parameters to the schema alone.

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 (US insider trades reported on SEC Form 4), names the covered population (officers, directors, 10% owners), the historical window (today back to 2006), and the source (SEC EDGAR Form 4 XML and insider data sets). This is clearly distinct from the congressional-trades sibling without needing to name it.

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?

Gives three concrete use cases (who is buying/selling a stock, insider activity before an event, market-wide cluster buys) plus explicit filter strategy: omit tickers/CIKs for the whole market and prefer tickers because a whole-market scan can take a minute or more. It stops short of naming an alternative tool for adjacent question types (e.g., general SEC filings), so no explicit when-not routing.

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