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

Vaquill-AI/vaquill-mcp

Official
by Vaquill-AI

Extract Citations from Text

extract_statute_citations
Read-only

Turn pasted legal text into distinct US statute, regulation, court rule, and constitution citations, optionally resolved to their sections; case citations are not included.

Instructions

Paste text (a brief, memo or answer) and get each distinct US statute, regulation, court rule and constitution citation, resolved to its section. Not case citations; extraction can miss one. Extraction is free (resolve=false); each distinct citation resolved is charged. Rows carry charStart/charEnd, rangeRole/rangePartner (range ends are two charged rows; interior rows are never charged) and counts.distinctSections. Up to 200,000 characters, never stored.

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": {
      "text": "<text>"
    },
    "name": "extract_statute_citations"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe text to read, 1 to 200,000 characters (a brief is about 30,000). Longer is a 422, never a silent truncation: a partial list reported as the whole is a wrong answer. Plain text; a body that is mostly binary is a 422.
stateNoThe document's jurisdiction as a two-letter state code (the forum of a filing). It scopes a citation that names no jurisdiction, such as `Civil Rule 56.1`; a citation naming its own is always checked against that one.
resolveNoResolve each distinct citation to its section (priced per distinct citation, see the endpoint's Cost). `false` returns the extraction alone, which is free.
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.
includeUnresolvedNo`false` drops rows that were sent to the resolver and did not resolve; rows with `skipped` set are always kept. `counts` and the charge are unchanged. Ignored when `resolve` is false.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.5.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare readOnly/openWorld/destructive; the description adds the costly parts an agent cannot infer: that extraction can miss citations, the per-distinct-citation charge model, that range-end rows are two charged rows while interior rows are never charged, the 200k hard limit returning a 422 rather than truncating, and that text is never stored. These are exactly the behavioral facts an agent needs before spending credits.

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?

Front-loaded with the purpose, then the accuracy caveat, then billing, then row semantics and limits — a sensible ordering with no filler sentences. It is dense (long semicolon-chained sentence about charStart/charEnd and rangeRole) and spends effort describing return-row fields even though an output schema exists.

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?

Covers the things an agent must know before calling: input size ceiling and failure mode, privacy (never stored), cost model, accuracy limitation, and idempotency-related billing behavior. With an output schema present, the description need not formally define return shapes, and what it does say about rows is supplementary rather than missing content.

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 text, state, resolve, Idempotency-Key and includeUnresolved thoroughly. The description adds only the cost implication of `resolve` (already noted in the schema itself) and otherwise spends its words on output row fields rather than parameter meaning. Baseline 3 applies.

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 verb (extract) and resource (US statute, regulation, court rule and constitution citations) and explicitly scopes out case citations. The distinction between free extraction (resolve=false) and charged resolution also separates it from the resolve_* siblings without needing to name them.

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 a clear usage context ('paste text — a brief, memo or answer') and a decision rule for the main mode switch: extraction is free with resolve=false, resolution is charged. It does not explicitly name an alternative tool (e.g. the batch resolver) for pre-collected citations, so the when-not guidance is implied rather than stated.

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