Skip to main content
Glama

Pandex

Read a law, an article or a decision

get_document
Read-onlyIdempotent

Read a document or one part of it in its official wording: a whole short text, one article (element), everything under a chapter, or the text as it stood on a date. One article of a law comes with the leading decisions on it: those cited most by the decisions that cite the article. Long documents come in pieces; the answer says how to continue.

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": {
      "id": "<id>"
    },
    "name": "get_document"
  }
}

Input Schema

NameRequiredDescriptionDefault
atNoRead the text in force on this day, YYYY-MM-DD. Default: the current text.
idYesAn id from a result, or an identifier or citation: an ECLI, a CELEX number, "BGB", "art. 6:162 BW".
fromNoContinue reading from this element id (given by a previous answer).
langNoTwo-letter language, for texts that exist in several.
casesNoWith one article of a law: the leading decisions on it. Default true.
elementNoThe part to read: an element id from a result or outline (art_6:162, par_823, chp_2) or its number as written ("6:162", "823").
historyNoWith element: also list the periods of every version of it.
max_tokensNoSize of the answer in tokens, 200–8000. Default 1500.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: an article returns leading decisions by default, long documents are chunked with continuation instructions, and history/at-date variants exist.

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?

Three dense sentences, front-loaded with the core action and granularities, then behavior, then continuation. No filler, though the middle sentence about leading decisions is slightly compressed and could be clearer.

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?

For an 8-parameter read tool with no output schema, the description covers the main modes (whole text, element, chapter, at-date), the default for cases, and the continuation mechanism. Minor gaps remain around language fallback and token-size behavior, but the essentials are present.

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 adds conceptual meaning by equating 'element' with an article or chapter and explaining that 'from' continues a previous answer and 'cases' attaches leading decisions. This clarifies how parameters combine rather than merely restating them.

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

Purpose4/5

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

States a specific verb (read) and resource (document) and enumerates the granularities it supports: whole short text, one article/element, a chapter, or a point-in-time version. This lets an agent distinguish it from search/outline siblings by scope, though it never names those siblings explicitly.

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?

Usage is implied by the granularity list and by 'Long documents come in pieces; the answer says how to continue', which hints at the pagination workflow. However, it gives no explicit when-to-use-vs-alternatives guidance (e.g. use search to find an id, use get_outline for structure) and no exclusions.

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.

Resources