Skip to main content
Glama
Vaquill-AI/vaquill-mcp

Vaquill-AI/vaquill-mcp

Official
by Vaquill-AI

State Session Laws

list_session_laws
Read-only

List a US state's session laws by jurisdiction and filter by session, approval/effective dates, text availability, series, or enactment outcome to find enacted acts or vetoed measures.

Instructions

List one US state's session laws (acts as enacted, v1 covers state acts only). jurisdiction is REQUIRED, a two-letter state code. Filter by session, approval date or effective date, for example everything taking effect on a date. Rows include laws whose text is not served (textStatus not_held or withheld); pass hasText=true for readable ones. Page with cursor = nextCursor. An empty page is still charged.

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": {
      "jurisdiction": "<jurisdiction>"
    },
    "name": "list_session_laws"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoOnly laws whose title or printed bill number contains this text, case-insensitive. A plain substring, with no stemming or ranking (use search_session_laws for that). Bill numbers match as printed (`S.F.No. 1552`). 3 to 100 characters.
isLawNotrue: only measures that are law. false: only numbered measures that are not (a vetoed bill, a pocket veto). Omit for both. A measure whose outcome is unsettled matches neither; use enactmentOutcome for those.
limitNoRows per page, 1 to 200; default 50. A page costs the same however many rows it holds, so a larger `limit` is cheaper per law. Outside the range is a 422.
orderNo`asc` (default) sorts by session code, then law id; `desc` is the exact reverse (newest session first). Law ids sort as text. Keep the same `order` across pages: changing it with a cursor is a 422.asc
cursorNoThe previous page's nextCursor, unchanged, sent with the same filters (limit may change). A cursor we did not issue, an expired one or one sent with different filters is a 422; restart without it. Omit for the first page.
seriesNoOnly laws in these numbering series (OR), as a result's series reports it; `general` is most states' ordinary chapter sequence. Not every state uses every series. An unknown value is a 422; a valid one that matches nothing is an empty, charged page.
hasTextNotrue: only laws whose text is served (textStatus held), the ones get_session_law_body returns. false: only laws without served text. Omit for both. Combines with textStatus by AND.
sessionNoOnly laws from this session, with the code exactly as session.code reports it (`2025R` regular, `2025S1` first special). Case-sensitive. A code that matches nothing returns an empty page, which is charged.
approvedToNoOnly laws approved (signed) on or before this date. Format `YYYY-MM-DD`, inclusive; it must be a real calendar date (`2025-02-30` is a 422). Like `approvedFrom`, it matches a derived `approvedDate` too.
textStatusNoOnly laws with this text status: `held` (served), `withheld` (held but kept back for a measured defect), `not_held` (known, no text) or `pending` (collected, not yet verified). Omit for all.
effectiveToNoOnly laws with an effective date on or before this date. Format `YYYY-MM-DD`, inclusive; it must be a real calendar date (`2025-02-30` is a 422). Overlap rule as for `effectiveFrom`. An end before `effectiveFrom` is a 422 (never charged).
approvedFromNoOnly laws approved (signed) on or after this date, `YYYY-MM-DD`, inclusive. A law with no printed approval date, or a derived one (approvedDateDerived: true), never matches. Pair with approvedTo; an end before the start is a 422.
jurisdictionYesREQUIRED. The two-letter code of the state to list, `dc` or `pr`, case-insensitive; one jurisdiction per call. `federal` or an unknown code is a 422. A state with no held session laws returns an empty page with a coverage note, not charged.
updatedSinceNoOnly laws whose record changed on or after this date (`YYYY-MM-DD`, midnight UTC, by updatedAt), for sync jobs. A day with no change returns an empty page, which is charged.
effectiveFromNoOnly laws with an effective date on or after this date, `YYYY-MM-DD`, inclusive; a law matches when its effectiveFirst to effectiveLast span overlaps the window. A law with no held effective date never matches, though it may be in force. For one day, send it as both bounds.
instrumentTypeNoOnly these kinds of measure (OR); `act` is an ordinary law. An unknown value is a 422; a valid kind that matches nothing is an empty, charged page.
Idempotency-KeyNoOptional, 16 to 255 visible ASCII characters (a UUIDv4 is ideal). A retry with the same key and request replays the original 2xx for 24 hours without charging again; the same key with a different request is rejected.
enactmentOutcomeNoOnly laws with one of these outcomes (OR), for example `vetoed` or `pocket_veto`, as enactmentOutcome reports it. An unknown value is a 422; a valid outcome that matches nothing is an empty, charged page.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.5.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, non-open-world), and the description adds genuinely non-obvious behavior: rows may be returned whose text is not served, and an empty page is still charged. Charging semantics and pagination via nextCursor are the kind of cost/behavior disclosure that annotations cannot carry. It stops short of covering idempotent retry behavior or rate limits.

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?

Five compact sentences, front-loaded with purpose then requirements, filters, caveats, and pagination. The date-filter example ('for example everything taking effect on a date') is slightly vague filler, but otherwise no sentence is wasted.

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

Completeness4/5

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

For an 18-parameter read tool with a full schema and an output schema, the description supplies the orientation an agent needs: required scope, filter families, cost behavior, and paging. Enumerating every filter is unnecessary given the schema, so the remaining gap is minor.

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 one of the 18 parameters in depth; the description only restates jurisdiction, date filtering, hasText, and the cursor-to-nextCursor mapping. The cross-field pagination hint is useful but largely duplicated; by the rubric this lands at the baseline.

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 specific verb and resource ('List one US state's session laws') and immediately scopes it ('acts as enacted, v1 covers state acts only'), which tells an agent exactly what corpus this returns. The 'one state' constraint and the required jurisdiction distinguish it from the cross-state and search siblings.

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 states the required parameter, the filtering dimensions (session, approval date, effective date) with a concrete example, and steers agents who want readable text to hasText=true. It does not explicitly name search_session_laws as the alternative for keyword ranking in the description body (that pointer lives only in the schema's q field), so guidance is clear but not fully closed.

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