Skip to main content
Glama

Merit — Ukrainian Law & Registers

Search Court Decisions (EDRSR)

ua_edrsr__search
Read-onlyIdempotent

Faceted full-text search over Ukrainian court decisions (ЄДРСР).

Hits are metadata with no reasoning text. What a court held comes only from get_document.

doc_type_name tells a procedural ruling (Ухвала) from a merits judgment without fetching it.

q is lemmatized inside the index; do not stem it first. Integer filters OR within, AND across.

A null total is the index not answering, not a no-match.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ua_edrsr__search"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoEvery word must occur; "quoted" text as a phrase.
sortNodate_desc: newest first.relevance
judgeNoExact judge name; Cyrillic case is folded.
limitNoMax rows to return (0-200); 0 returns the count alone.
offsetNo
statusNoDecision status codes.
date_toNoInclusive ISO date.
instanceNo1 cassation, 2 appellate, 3 first instance.
date_fromNoInclusive ISO date.
court_codeNoCourt codes.
cited_dokidNoOnly decisions citing these ua_law document ids.
justice_kindNoJustice-kind codes.
category_codeNoCase-category codes.
judgment_codeNoJudgment-form codes; see list_dict_values.
resolution_depthNoDocument-level rollup: none, article, clause.
exclude_judgment_codeNoCodes to drop; 5 is Ухвала, the procedural ruling.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / q / description
      Previous value: -"Free-text query, in the user's own words."New value: +"Every word must occur; \"quoted\" text as a phrase."
    • addedInput schema / properties / sort
      Added value: +{
      +  "default": "relevance",
      +  "description": "date_desc: newest first.",
      +  "enum": [
      +    "relevance",
      +    "date_desc",
      +    "date_asc"
      +  ],
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds behavior the annotations cannot: hits contain no reasoning text, a null `total` means index failure rather than zero matches, and integer filters OR within a field but AND across fields. Those are exactly the non-obvious traits that would otherwise cause misinterpretation of results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Six short lines, each carrying a distinct fact, with the resource identification front-loaded and the failure-mode caveat last. No sentence restates the tool name or the annotations, and nothing is padded.

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 a 16-parameter search with no output schema, the description covers the critical unknowns: result shape is metadata-only, a key response field (`doc_type_name`) is named, filtering logic is explained, and the null-`total` failure mode is documented. It does not describe pagination behavior or the shape of individual hit fields beyond that one name, which is a modest gap rather than a blocking one.

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 94%, so the baseline is 3; the description earns above that by adding semantics the schema lacks — `q` is lemmatized server-side so callers must not stem, and the cross-field/intra-field boolean behavior of the array filters is stated explicitly. It does not explain `total` semantics in relation to `limit=0` or offset paging beyond that, so it is not exhaustive.

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?

First line names a specific verb and resource ("Faceted full-text search over Ukrainian court decisions (ЄДРСР)") and frames the result type ("Hits are metadata"). It also distinguishes itself from the sibling `get_document` by stating that holdings come only from that tool, so an agent can pick between them without opening a schema.

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?

It gives clear routing: this tool is for locating decisions, `get_document` is for reasoning text, and `doc_type_name` lets the agent screen Ухвала vs merits judgment before spending a fetch. It does not name other plausible alternatives (e.g., `ua_edrsr__lookup_case`, `ua_edrsr__get_court_practice`) or state when this search is the wrong entry point, so it stops short of a full when/when-not/alternatives treatment.

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.