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

Vaquill-AI/vaquill-mcp

Official
by Vaquill-AI

State Session Law Text

get_session_law_body
Read-only

Fetches the exact printed text of a US state session law page by page and flags amendatory markup so struck language is not mistaken for enacted law.

Instructions

The text of one US state session law exactly as printed, about 30,000 characters per page; follow nextCursor while hasMore is true, each page charged. Check amendatoryMarkup: if lost, struck language may read as law. A withheld or not-held law answers available: false with a reason and is not charged: withheld means we hold the text but a measured defect keeps it back, so read the source instead.

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": {
      "session_law_id": "<session_law_id>"
    },
    "name": "get_session_law_body"
  }
}

Input Schema

NameRequiredDescriptionDefault
cursorNoThe previous page's nextCursor, unchanged; omit for the first page. Tied to the exact text: an unknown or expired cursor is a 422, one from before the text was re-collected is a 409 (start again). Never charged. Send cursor or startChar, not both.
versionNoRead this version of the text instead of the current one: a `version` from get_session_law_versions. Omit for the current version. A cursor belongs to its version (a 409 on another), an unlisted number is a refunded 404 and a value below 1 is a 422. A withheld law's older version needs `includeUnverified=true`, as its current text does.
startCharNoStart the page at this 0-based character offset (the scale of pageStart and totalChars) to jump to a known place without paging. Same page size and price as any page. Send startChar or cursor, not both. At or past the end of the text is a 422, refunded.
session_law_idYesA state session law id, e.g. `SSL_MN_2025R_G_Y2025_C1`, from list_session_laws or get_session_law. Pass the id, not a citation: resolve a citation with get_session_law first. Federal `SAL_` ids 404.
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.
expectTextSha256NoThe textSha256 you read under, lowercase hex, 16 to 64 characters. If the text has since been re-collected the answer is a 409 and nothing is charged. Use with startChar, which has no version binding of its own.
includeUnverifiedNoOpt in to the text of a law we hold but do not serve (`textStatus: withheld`). Default `false`: it answers `available: false`. With `true` the text is returned when the reason is one we can label, and every page carries `textReliability`, `reasonCode` and a `notice` to show beside it: the text MAY show deleted or vetoed law as enacted. A law whose licence bars use, or whose text failed validation, is never served.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.5.0

TDQS

A3.9/5.0
Behavior4/5

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

The annotations only declare readOnlyHint and destructiveHint=false; the description adds the cost model ('each page charged'), the non-charge path for withheld or not-held laws, and the substantive risk that 'struck language may read as law' if amendatoryMarkup is lost. That is meaningful behavior beyond the annotations. It omits idempotent-replay and stale-text 409 semantics, which live only in the schema.

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?

Four dense sentences, front-loaded with what the tool returns and its page size, then billing, then the amendatoryMarkup hazard, then the withheld-law branch. No sentence is filler, though the final sentence is long and packs three distinct conditions into one clause chain.

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?

With an output schema present, the description does not need to enumerate return fields, and it still flags the key ones (nextCursor, hasMore, amendatoryMarkup, available) plus the billing consequence of paging. What remains thin is guidance on navigating the six optional parameters — version selection, startChar jumping, and hash-verified re-reads — which matter for correct invocation of a 7-parameter tool.

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 parameter meaning is already fully documented in structured form and the baseline applies. The description only echoes cursor (as nextCursor/hasMore) and gestures at the withheld/includeUnverified path; version, startChar, expectTextSha256 and Idempotency-Key are never touched, so it adds little beyond the schema.

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 opening clause names the exact resource ('the text of one US state session law exactly as printed') and its granularity ('about 30,000 characters per page'), so an agent knows this returns full text rather than metadata. This is clearly separable from siblings like get_session_law and get_session_law_versions, which serve the id and version list rather than body text.

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

Usage Guidelines3/5

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

It gives real operational guidance for the paging loop ('follow nextCursor while hasMore is true') and a fallback for withheld text ('read the source instead'). What it never states is the routing decision against siblings: when to use get_session_law to resolve an id first, or get_session_law_versions to pick a version — those cues exist only in the schema parameter descriptions.

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