Skip to main content
Glama

Arkanum Data: SEC insider trades

Search insider trades by year

search_insider_history
Read-only

Every open-market insider buy and sale in one calendar year, from SEC's Insider Transactions Data Sets: Pro covers 2006 to now, Hobby 2023 to now. Sorted by value (largest first) by default, or by filed or traded date. Call once per year; for a range of years, call each year. Trades whose price looks like a typo in the filing are left out and counted in flagged_left_out (include_flagged=true shows them). Takes a few seconds.

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": {
      "year": "<year>"
    },
    "name": "search_insider_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
sideNo
sortNovalue
yearYese.g. 2008
limitNo
tickerNo
insiderNoPart of the insider's name
plannedNo
min_valueNo
insider_cikNo
include_flaggedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior5/5

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

Goes well beyond the annotations: it names the upstream data source, discloses coverage tiers by subscription level, states the default sort and alternatives, warns that typo-priced trades are silently excluded but counted in flagged_left_out (with include_flagged=true to surface them), and sets latency expectations ('Takes a few seconds'). The filtering behavior is exactly the kind of hidden trait an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four dense sentences with no filler, front-loaded with scope and source, then guidance, then the flagged-trades caveat and latency. Every clause carries operational information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists and 8 of 10 parameters are unexplained, so the agent still lacks semantics for most filters and for how limit interacts with the default 20. It partially compensates by describing the flagged_left_out return field and coverage windows, but a 10-parameter tool warrants more.

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

Parameters2/5

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

Schema description coverage is only 20% across 10 parameters, so the description must compensate and largely does not. It adds real meaning only for sort (value/filed/traded), include_flagged, and year-range coverage; side, ticker, insider, insider_cik, planned, min_value, and limit are left to bare schema names or inline defaults.

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?

States a specific verb+resource with tight scope: 'Every open-market insider buy and sale in one calendar year, from SEC's Insider Transactions Data Sets.' That is far more informative than the name alone. It does not, however, differentiate itself from siblings like search_insider_trades or latest_insider_trades, so an agent must infer the boundary.

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 concrete operational guidance: 'Call once per year; for a range of years, call each year,' plus tier coverage (Pro 2006+, Hobby 2023+), which tells an agent when the tool will return nothing. It stops short of saying when a sibling such as search_insider_trades would be the better choice.

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