Skip to main content
Glama

Merit — Ukrainian Law & Registers

Get Legal Provision Text

ua_law__get_unit_fulltext
Read-onlyIdempotent

Unit text, paged.

truncated: not the whole unit; next_cursor (none on the last page) is the cursor for more. Pages end after a paragraph, else a space, else mid-word (a tiny max_chars). Only page 1 lists parts, sub-units with their own urn, unless parts_offset is passed.

text: null with status 'edition_text_unavailable' (edition not stored) or 'extraction_failed' (unit not cut out) is a unit that DOES exist -- not a repeal. No unit at that address answers 'not_found'.

text_since: the edition this text first reads so; edition_date only dates the act's latest change.

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": {
      "urn": "<urn>"
    },
    "name": "ua_law__get_unit_fulltext"
  }
}

Input Schema

NameRequiredDescriptionDefault
urnYesUnit URN, from get_document_toc.
cursorNoA `next_cursor`.
max_charsNoPage size; 0: `parts` only.
parts_offsetNoStart of `parts`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior5/5

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

With annotations only covering read-only/idempotent safety, the description supplies the substantive behavior: truncation via `truncated`/`next_cursor`, page-break rules that can split mid-word at tiny `max_chars`, `parts` appearing only on page 1 unless `parts_offset` is set, and the critical distinction that `text: null` with 'edition_text_unavailable'/'extraction_failed' means the unit exists rather than being repealed, while 'not_found' means no unit at that address. It also decodes `text_since` versus `edition_date`. This is exactly the context an agent cannot get from the annotations.

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?

Dense but purposeful — nearly every clause carries a distinct fact, and the headline 'Unit text, paged' is front-loaded before the paging mechanics. The telegraphic, backtick-heavy register and sentence fragments cost some readability, but there is little wasted wording.

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 no output schema, the description must carry the response burden, and it does: it explains every notable output field (`truncated`, `next_cursor`, `parts`, `text`, `text_since`, `edition_date`) and the status semantics. It stops short of describing the text's rendering/formatting or how to obtain the starting `urn` beyond the schema's note pointing at get_document_toc.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description genuinely extends it: it ties `cursor` to `next_cursor`, explains that `max_chars` can force mid-word breaks when tiny, and reveals the non-obvious rule that `parts` are listed only on page 1 unless `parts_offset` is supplied. Only `urn` (already fully described in schema) goes unelaborated.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The front-loaded phrase 'Unit text, paged' does identify the resource (a legal unit's full text) and the paged delivery, but it never spells out the verb or what a 'unit' is, and it draws no boundary against close siblings such as ua_law__get_unit or ua_law__get_units_fulltext. An agent must infer from the name alone whether this returns text or metadata.

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

Usage Guidelines2/5

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

There is no explicit when-to-use guidance and no pointer to an alternative for bulk retrieval of multiple units or for lighter metadata lookups. The only operational cues ('cursor' for more, 'parts_offset' for later pages) are mechanical paging instructions rather than tool-selection guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.