Skip to main content
Glama

Coldpine: Congressional Stock Disclosures

by io.coldpine
OverviewDiscussionsAdmin

Cluster buys and sells

cluster_trades
Read-onlyIdempotent

Stocks that several members of Congress traded in the same direction inside a rolling window (Coldpine's cluster detection, same definition as the bot). Returns ticker, direction, distinct member count, trade count, date span, summed disclosed amount range and the member names. Same data as coldpine.io/research/biggest-cluster-buys-in-congress. Use it for 'what are several members buying (or selling) at once'; for everyone who ever traded one given stock use get_stock instead. The window counts back from the most recent trade date on record, not from a date you choose, and clusters come back largest first by distinct members. A person is counted once per cluster however many trades they made. Overlap in timing is a description of the filings, not evidence of coordination. Access: needs the agent token from a free Coldpine account, sent as 'Authorization: Bearer '; without it the call returns setup steps instead of data. Read-only, cached for up to an hour.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum clusters to return, 1 to 50. Default 10.
directionNoWhich side to cluster: 'purchase' for stocks several members bought, 'sale' for stocks several sold. Default 'purchase'. One direction per call.purchase
min_membersNoSmallest number of distinct members that makes a cluster, 2 to 20. Default 3. Raise it to keep only the broadest overlaps.
window_daysNoLength of the look-back window in days, 1 to 365, ending at the latest trade date on record. Default 90. A longer window finds more and larger clusters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / direction / description
      Added value: +"Which side to cluster: 'purchase' for stocks several members bought, 'sale' for stocks several sold. Default 'purchase'. One direction per call."
    • addedInput schema / properties / limit / description
      Added value: +"Maximum clusters to return, 1 to 50. Default 10."
    • addedInput schema / properties / min_members / description
      Added value: +"Smallest number of distinct members that makes a cluster, 2 to 20. Default 3. Raise it to keep only the broadest overlaps."
    • addedInput schema / properties / window_days / description
      Added value: +"Length of the look-back window in days, 1 to 365, ending at the latest trade date on record. Default 90. A longer window finds more and larger clusters."
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Beyond annotations (read-only, idempotent, non-destructive), the description adds materially: authentication via Bearer token and the failure mode without it (setup steps), caching for an hour, rolling window anchored to latest trade date, ordering, per-person deduplication, and the coordination caveat. No contradiction with annotations.

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?

The description is a dense but well-ordered paragraph: definition, output, usage, key behavioral constraints, and access. Every sentence carries information needed for correct invocation or interpretation; there is no filler or repetition of schema defaults.

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 still names all returned components (ticker, direction, member count, trade count, date span, amount range, member names). It also covers auth, error behavior, caching, and data interpretation, so an agent has enough context to call and understand the result.

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 100%, so per-parameter basics are already documented. The description adds meaning beyond the schema by explaining that window_days counts back from the most recent trade date on record, that people are counted once per cluster regardless of trade count, and that ordering is by distinct member count.

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 description opens with a precise definition: stocks several members of Congress traded in the same direction inside a rolling window, and enumerates the returned fields. It also names the sibling get_stock as the alternative for single-stock queries, making the tool's scope unmistakable.

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 gives an explicit usage frame ('what are several members buying (or selling) at once') and names the specific alternative and its condition: for everyone who ever traded one given stock, use get_stock. That is direct when-to-use/when-not-to-use guidance.

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

All Coldpine: Congressional Stock Disclosures 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