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

Vaquill-AI/vaquill-mcp

Official
by Vaquill-AI

Session Law Change Feed

get_session_law_changes
Read-only

Poll a cursor-based sync feed of US state session-law changes—newly served, corrected, withdrawn, or merged—and use returned IDs to fetch full law text.

Instructions

A sync feed of the US state session-law registry: every law that began to be served, gained text, was corrected, unserved, withdrawn or merged, oldest first. Start with sinceId=0, then pass the returned cursor while hasMore is true. detectedAt is when we recorded the change, never an effective date. State laws only. An empty page is still charged. Read a law from the feed with get_session_law or get_session_laws_batch.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_session_law_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMost entries on this page: 1 to 200, default 50. The price is per page, however many entries it holds, so a larger page is cheaper per entry. Out of range is a 422 and is never charged.
sinceIdNoReturn entries with an id greater than this. Send 0 (the default) to start, then the cursor of your last page; exact and immune to clock skew. A value past the newest id returns an empty page, which is charged.
jurisdictionNoLimit the feed to one two-letter state code, `dc` or `pr`; omit for all. `federal` or an unknown code is a 422, never charged. The cursor is a position in the whole feed, so a filtered page can skip ids.
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.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.5.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare a safe read (readOnlyHint=true, destructiveHint=false, openWorldHint=false), and the description adds material context beyond them: 'detectedAt is when we recorded the change, never an effective date' prevents a serious semantic misread, and 'An empty page is still charged' discloses the billing consequence of polling past the newest id. Ordering ('oldest first') and the terminal condition (hasMore) round out the behavior an agent needs to drive the loop safely.

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?

Front-loaded with the core identification, then procedure, then the two critical caveats (detectedAt vs. effective date, charged empty page), then the follow-up tools. Six short clauses, no repetition of schema text, nothing that could be dropped without losing information.

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?

An output schema exists, so return-shape details are correctly delegated. The description covers everything else an agent needs: what the feed contains, ordering, how to page, when to stop, billing implications of empty pages, the timestamp trap, and which tool to call next to read a law.

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 coverage is 100%, so parameters are already fully documented (limit ranges and pricing, sinceId cursor semantics, jurisdiction enum and filter/cursor interaction, idempotency key). The description mainly reinforces the cursor loop described in the schema; it adds 'oldest first' ordering and the page-loop contract but nothing about limit or jurisdiction beyond what is already structured. Baseline 3 is appropriate.

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?

States a specific artifact ('a sync feed of the US state session-law registry') and enumerates exactly what event types appear in it (began to be served, gained text, corrected, unserved, withdrawn, merged), plus the ordering ('oldest first'). This is clearly distinguishable from siblings like list_session_laws or search_session_laws because it is framed as an incremental change feed rather than a query.

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?

Gives explicit procedural guidance: 'Start with sinceId=0, then pass the returned cursor while hasMore is true', and routes the agent to get_session_law / get_session_laws_batch to read the underlying law. Scope exclusion 'State laws only' is also stated. It stops short of contrasting with the stateful listing tools (e.g. when to prefer list_session_laws over the feed), so not quite a full when/when-not/alternatives treatment.

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