Congress Member Votes

Member Attendance Party Line

member_attendance_party_line

Read-onlyIdempotent

ANSWERS "how many votes did Rep. X miss", "how often does X vote with their party", "party unity score" -- attendance and party-line share for ONE member (House, or a senator with chamber "senate") over a session (or a roll range), computed from the U.S. House Clerk's roll-call votes or, for the Senate, the Congressional Record's printed roll calls. Nothing is returned as a bare percentage: attendance gives its denominator (recorded roll calls the member was on the roll for; quorum calls, Speaker elections and Senate rolls that could not be derived are excluded and counted; rolls before the member was seated or after they left are excluded and counted -- absence from the roll is NOT treated as Not Voting) and splits yea/nay, present and Not Voting. Party line gives two figures, each with its own denominator and exclusions: share of yea/nay votes cast with the member's party majority (a strict majority of that party's yea/nay voters; ties excluded and counted), and party unity (only the roll calls where a majority of Democrats opposed a majority of Republicans). If a figure cannot be computed from the rolls in range (member on none, no party-splitting votes, independent) it is null with a stated reason, never 0% or 100%. Independents (including the Senate's two caucusing independents) have no D-versus-R majority to compare against, so their party-line figure is null with that reason.

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": {
      "session": 2,
      "congress": 119,
      "bioguide_id": "P000197"
    },
    "name": "member_attendance_party_line"
  }
}

Input Schema

Name	Required	Description
`name`	No	Surname as the Clerk prints it, e.g. "Pelosi"; combine with state when several members share it.
`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 of the range (default: last roll covered).
`congress`	No	Congress number, e.g. 119. Default: the newest held.
`from_roll`	No	First roll number of the range (default 1).
`bioguide_id`	No	Bioguide id, e.g. "P000197".

Output Schema

Name	Required	Description	Default
`found`	No
`range`	No
`member`	No
`source`	No
`chamber`	No
`session`	No
`congress`	No
`attendance`	No
`data_as_of`	No
`live_topup`	No
`party_line`	No
`definitions`	No
`rolls_covered`	No
`excluded_rolls`	No
`rolls_in_range`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 25, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations already cover read-only/idempotent/non-destructive, and the description still adds substantial behavioral disclosure: which rolls are excluded and counted, that absence is not treated as Not Voting, that quorum calls and Speaker elections are dropped, that ties are excluded, and that uncomputable figures return null with a reason rather than 0% or 100%. That is exactly the kind of denominator and edge-case transparency an agent needs to trust and interpret results.

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

Conciseness3/5

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

Purpose is front-loaded via the quoted question exemplars, which is good structure, but the remainder is a dense wall of clauses that mixes methodology with return-value semantics. Since an output schema exists, the long explanation of what attendance and party-line figures contain partly duplicates structured data and could be tightened.

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 an 8-parameter, zero-required analytics tool with an output schema, the description supplies the missing interpretive layer: data sources per chamber, denominator definitions, exclusion handling, and null semantics for independents and uncomputable cases. An agent can call it and correctly explain its output without further context.

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 description coverage is 100%, so the schema already documents every parameter (name, state, chamber, session, from_roll/to_roll, congress, bioguide_id). The description adds only a light framing — that the window is a session or a roll range, and that chamber selects the House Clerk versus Congressional Record source — which is marginal beyond what the schema states. 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?

States a specific computed resource — attendance and party-line share for one member over a session or roll range — and anchors it in concrete question phrasings ("how many votes did Rep. X miss", "party unity score"). The verb/resource pairing is unambiguous, but no sibling tool (e.g. member_vote_positions or roll_call_positions, which return individual positions) is named, so the agent must infer the split between aggregate metrics and per-vote listings.

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?

The opening question exemplars effectively communicate when to reach for this tool, and the description notes the House-vs-Senate source difference and that independence makes the party-line figure null. It gives clear usage context but never states exclusions against alternatives or prerequisites like needing a resolvable member identity first.

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.