Skip to main content
Glama

trades

by com.potomacledger
OverviewDiscussionsAdmin

search_trades

Read-onlyIdempotent

Search disclosed trades by person, ticker, branch, role (Senate/House/title), buy/sell, conflict flag, minimum dollar amount, and date window. Returns newest first.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
roleNoChamber for Congress (Senate / House) or title substring for executive (President / Secretary / Administrator…), case-insensitive
typeNoTransaction direction: "buy", "sell" (includes partial sales), or "exchange". Case-insensitive.
limitNoMax results per page (default 100, capped 500)
sinceNoISO date lower bound (disclosure/trade date)
untilNoISO date upper bound
branchNoEither "congress" or "executive" (case-insensitive)
offsetNoSkip the first N matching rows — pair with limit to page through large result sets
personNoMember or official name (substring, case-insensitive)
tickerNoStock ticker, e.g. NVDA (case-insensitive)
conflictNoOnly trades flagged as a potential conflict
minAmountNoMinimum upper-bound of the disclosed dollar range

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / branch / description
      Added value: +"Either \"congress\" or \"executive\" (case-insensitive)"
    • removedInput schema / properties / branch / enum
      Removed value: -[
-  "congress",
-  "executive"
-]
    • changedInput schema / properties / ticker / description
      Previous value: -"Stock ticker, e.g. NVDA"New value: +"Stock ticker, e.g. NVDA (case-insensitive)"
    • changedInput schema / properties / type / description
      Previous value: -"Transaction direction; \"sell\" includes partial sales"New value: +"Transaction direction: \"buy\", \"sell\" (includes partial sales), or \"exchange\". Case-insensitive."
    • removedInput schema / properties / type / enum
      Removed value: -[
-  "buy",
-  "sell",
-  "exchange"
-]
  2. Changed3 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"Max results (default 50, capped 200)"New value: +"Max results per page (default 100, capped 500)"
    • addedInput schema / properties / offset
      Added value: +{
+  "description": "Skip the first N matching rows — pair with limit to page through large result sets",
+  "type": "number"
+}
    • addedInput schema / properties / role
      Added value: +{
+  "description": "Chamber for Congress (Senate / House) or title substring for executive (President / Secretary / Administrator…), case-insensitive",
+  "type": "string"
+}
  3. Changed2 schema fields changed
    • addedInput schema / properties / type / description
      Added value: +"Transaction direction; \"sell\" includes partial sales"
    • changedInput schema / properties / type / enum
      Previous value: -[
-  "buy",
-  "sell"
-]New value: +[
+  "buy",
+  "sell",
+  "exchange"
+]
  4. First observed

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description adds only the ordering detail 'Returns newest first.' No other behavioral traits (e.g., pagination behavior, rate limits, effect of filters) are disclosed beyond what annotations provide. This is adequate given the 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 single concise sentence that efficiently enumerates key filters and ordering. No wasted words, and it is front-loaded with the verb and resource.

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

Completeness2/5

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

Given the absence of an output schema, the description does not explain what fields are returned in the results (e.g., trade date, amount, asset type). It only states 'Returns newest first', leaving the agent to guess the response structure. For a tool with 11 parameters and no output schema, this is insufficient.

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?

All 11 parameters have descriptions in the input schema (100% coverage), so the description adds minimal new information. It merely re-lists some parameter categories without enhancing meaning. Baseline 3 is appropriate.

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?

The description clearly states the tool searches disclosed trades with specific filters (person, ticker, branch, role, buy/sell, conflict, etc.) and returns results newest first. The verb 'search' and list of filters make the purpose clear, but it does not explicitly differentiate from sibling tools like get_person_trades or list_recent_trades.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description lists many filters but provides no guidance on when to use this tool versus alternatives. It does not mention scenarios where one of the sibling tools (e.g., get_ticker_activity, list_conflicts) would be preferable, nor does it specify prerequisites or exclusions.

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

All trades 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