Skip to main content
Glama

Fuzzzy Law: Georgian law

get_court_decision

Read-onlyIdempotent

Read a stored court decision in full, twenty passages per call, by the id from find_court_practice or its printed case number. Read it before you describe what the court decided. The text is as the court published it: the Supreme Court prints parties as initials, the Constitutional Court prints their names. გადაწყვეტილების სრული ტექსტი ნაწილ-ნაწილ, იმ სახით, როგორც სასამართლომ გამოაქვეყნა.

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_court_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesA decision id from find_court_practice (case:court_practice:ას-398-398-2018) or a printed case number (ას-398-398-2018, or 3/1/1459 for a Constitutional Court judgment).
from_passageNoPassage to start from; use next_passage to read on.

Output Schema

NameRequiredDescriptionDefault
foundYes
noticeNoეს არის კანონის ტექსტი და წყარო, არა იურიდიული კონსულტაცია. ოფიციალური ტექსტი: matsne.gov.ge. This is law text and its source, not legal advice. The official text is on matsne.gov.ge; for important decisions consult a lawyer.
messageNo
decisionNo
passagesNo
next_passageNoPass as from_passage to read on; absent at the end.
total_passagesNo
freshness_warningNoSet when that check is overdue or its date is unknown; pass the warning on with the answer.
data_current_as_ofNoDate (ISO) the stored law texts were last confirmed against matsne.gov.ge. Tell the person this date.
law_since_decisionNoThe stored law articles this decision cites and whether their wording changed after the decision date.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already establish readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description still adds genuinely new behavior: the 20-passage page size, that text is verbatim as published, and that court-specific formatting differs (Supreme Court uses initials, Constitutional Court uses names) — a real trap for downstream quoting. It does not say what happens at the end of the document or whether an empty page signals completion.

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?

The English portion is front-loaded and efficient, leading with the verb and the call budget. However, the trailing Georgian sentence fully restates the English content, doubling length for an agent that only needs one statement of the same facts.

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 annotations, an output schema and full schema coverage already present, the description only needs to supply the pagination model, identifier provenance and verbatim-text caveat — all of which it does. The only omission is terminal behavior when pagination runs past the last passage.

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 coverage is 100%, so both parameters and the id formats are already fully documented in structured fields, warranting the baseline 3. The description reinforces the pagination model with the 20-passage unit but adds no syntax or constraint beyond what the schema states.

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?

States a specific verb and resource ('Read a stored court decision in full') plus the batching unit ('twenty passages per call') and the accepted identifiers. It implicitly contrasts with the retrieval sibling find_court_practice by naming it as the source of the id, so an agent can tell lookup from full-text read without opening either 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?

Gives an explicit precondition — 'Read it before you describe what the court decided' — which tells the agent when this tool is mandatory rather than optional. It also points to next_passage for continuation and accepts a printed case number as an alternative entry path. It stops short of naming when not to use it (e.g. for searching by topic), leaving that to inference.

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.