Congress Member Votes

Member Vote Positions

member_vote_positions

Read-onlyIdempotent

ANSWERS "how did Rep. X vote on bill Y" / "what were X's last 20 votes" / "did X vote against the budget resolution" -- one member's recorded position (Yea, Nay, Present, Not Voting, or not on the roll) on roll calls, newest first -- House members from the U.S. House Clerk's roll-call votes, senators (chamber "senate") from the Congressional Record, where the Senate's roll calls are printed. Filter by bill (e.g. "H R 1"), question_contains (matched against question, bill number and description) or a roll range. Quorum calls, Speaker elections and Senate rolls whose record could not be derived are left out unless include_non_recorded is true. Every response names its chamber, congress, session, the last roll it covers and data_as_of. An unknown member or a Congress/session not held returns a named reason, never an empty list.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "bill": "H CON RES 14",
      "session": 1,
      "congress": 119,
      "bioguide_id": "P000197"
    },
    "name": "member_vote_positions"
  }
}

Input Schema

Name	Required	Description
`bill`	No	Legislation number as the Clerk prints it, e.g. "H R 1", "H J RES 104", "S 2403" (punctuation and spacing ignored; exact match).
`name`	No	Surname as the Clerk prints it, e.g. "Pelosi"; combine with state when several members share it.
`limit`	No	Rolls to return (default 20, max 50).
`state`	No	Two-letter state code to disambiguate a surname.
`chamber`	No	"house" (default) or "senate". The two chambers number their roll calls independently.
`session`	No	1 or 2. Default: the newest held for the default Congress.
`to_roll`	No	Last roll number to consider.
`congress`	No	Congress number, e.g. 119. Default: the newest held.
`from_roll`	No	First roll number to consider.
`bioguide_id`	No	Bioguide id, e.g. "P000197".
`question_contains`	No	Case-insensitive text to match in the vote question, bill number or description, e.g. "suspend the rules", "continuing appropriations".
`include_non_recorded`	No	Include quorum calls and Speaker-election rolls (default false).

Output Schema

Name	Required	Description	Default
`note`	No
`found`	No
`votes`	No
`member`	No
`source`	No
`chamber`	No
`session`	No
`congress`	No
`returned`	No
`data_as_of`	No
`live_topup`	No
`matched_rolls`	No
`rolls_covered`	No
`tally_over_returned_rolls`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 25, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Beyond the read-only and idempotent annotations, the description discloses data sources (House Clerk vs. Congressional Record), ordering (newest first), exclusion rules for quorum calls and Speaker elections, response metadata (chamber, congress, session, last roll, data_as_of), and explicit error behavior. This is rich operational context 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.

Conciseness4/5

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

The description is front-loaded with the core answer and is dense with useful information. It runs long and could be tightened, but every sentence contributes to correct invocation or interpretation.

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?

Given the tool’s complexity (12 optional params, two chambers, data provenance) and the presence of an output schema, the description provides everything an agent needs: sources, exclusions, response fields, and failure semantics.

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 the baseline is 3. The description adds meaning by explaining that `question_contains` matches question, bill number, and description, that roll ranges are supported, and that `include_non_recorded` also includes Senate rolls whose record could not be derived—details beyond the schema’s wording.

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 specific verb and resource: retrieving one member's recorded vote positions on roll calls, with source distinctions for House and Senate. It distinguishes itself from roll-call-centric siblings by emphasizing 'one member's recorded position', though it does not explicitly name sibling tools like roll_call_positions.

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?

It provides clear usage context through example questions ('how did Rep. X vote...', 'what were X's last 20 votes') and describes filters, exclusions, and error behavior. However, it lacks explicit guidance on when to prefer this tool over alternatives such as roll_call_positions.

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

All Congress Member Votes tools Inspect

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.