Skip to main content
Glama

check_draft

Verify every citation, attributed quotation, negative treatment, and authority currency in a draft opinion, memo, or brief, returning severity-ranked flags for review.

Instructions

One-call cite-check of a draft opinion, memo, or brief: verify every citation, every attributed quotation, negative treatment of cited cases, and the currency of cited authorities — a severity-ranked flag report.

Checks (all on by default, select with checks): citations — every ND case cite resolves (typo catch), case-name drift vs the canonical caption, missing neutral cite, statutory subsection pinpoints validated against the provision; quotations — every quotation attributed to a nearby cite is located in that authority's text (typography-tolerant; word-level diff on mismatch); statutes/rules/const quotes are also retried against OTHER captured versions to catch quoting since- amended text; treatment — cited cases run through the citator; possible-negative / distinguished citing sentences surface (same engine as detect_overruled_in_draft, which remains the cheap treatment-only pass); currency — repealed / superseded / not-in-force authorities, checked at as_of_date when given (offense/contract date); and a cited case that cites an N.D.C.C. section but was filed before the section's current text took effect (construed_earlier_version, S4).

Severities: S1 misquotation or quote-of-superseded-text · S2 citation doesn't resolve · S3 possible negative treatment · S4 authority currency / bad pinpoint · S5 name drift / missing neutral cite.

Heuristic and NON-authoritative throughout: extraction is regex-based (foreign/federal authority is listed as unchecked, not verified), quote attribution follows the nearest-cite convention and can misattribute, bracketed alterations and ellipses in quotes surface as differences, and treatment signals are sentence-local. Read every flag's context before acting on it. A draft spanning several operative dates needs per-authority lookup_authority calls — as_of_date anchors the whole draft.

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": {
      "draft_text": "<draft_text>"
    },
    "name": "check_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
checksNoSubset of ["citations","quotations","treatment","currency"] (default all).
max_casesNoCitator budget — max distinct cases scanned (default 60).
as_of_dateNoOptional ISO date anchoring authority currency (default: current law).
draft_textYesThe draft's full text.
max_quotesNoMax attributed quotations verified (default 40).
scan_limitNoCiting-opinion scan cap per case (default 200).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.4.0

TDQS

A4.1/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden — and it does this unusually well: it discloses that extraction is regex-based, that foreign/federal authority is 'listed as unchecked, not verified', that quote attribution follows a nearest-cite convention and can misattribute, that bracketed alterations/ellipses surface as false differences, and that treatment signals are sentence-local. However, it says nothing about runtime cost, latency, or failure modes despite max_cases/max_quotes/scan_limit implying a costly citator sweep, which is the main behavioral gap remaining.

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?

Front-loaded with a one-line summary and nicely organized by check name, but the check block is long and densely parenthetical, so key operational facts (heuristic/non-authoritative caveat, severity map) sit below a wall of detail. The content mostly earns its place given the tool's complexity, though it could be tightened without loss.

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 values needn't be explained; instead the description supplies the severity taxonomy (S1–S5) that makes the report interpretable, plus explicit caveats about the multi-date limitation and unchecked foreign/federal authority. For a six-parameter, multi-stage verification tool this is complete enough to call correctly.

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 baseline is 3. The description adds real meaning for `checks` (the valid subset and the four named checks) and for `as_of_date` (it anchors the entire draft, not individual authorities, and defaults to current law). It adds little beyond the schema for the three budget parameters (max_cases, max_quotes, scan_limit), which are already self-documenting.

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?

Opens with a specific verb+resource+scope: 'One-call cite-check of a draft opinion, memo, or brief' and enumerates the four check families it performs. It explicitly positions itself against siblings — detect_overruled_in_draft is named as 'the cheap treatment-only pass' and lookup_authority as the per-authority alternative — so an agent can distinguish it without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

States that all checks are on by default and are selectable via `checks`, gives the explicit condition for using the sibling tool (per-authority lookup_authority when a draft spans several operative dates), and explains that `as_of_date` anchors the whole draft. When-to-use and when-to-deviate are both covered.

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