Skip to main content
Glama

translate_text

Translate text between 8 languages, using direct pairs when available and automatic English pivot for others. Optionally preserve document structure for Czech-English translations.

Instructions

Přeloží text přes Charles Translator (LINDAT) — 8 jazyků, 17 přímých párů + auto EN-pivot pro nepřímé páry.

Podporované jazyky: ``cs`` (čeština), ``en``, ``fr``, ``de``, ``pl``,
``ru``, ``uk`` (ukrajinština), ``hi`` (hindština).

**Přímé páry** (17): cs↔en (+doc), cs↔uk, cs↔ru, en↔fr, en↔de, en↔ru,
en↔pl, en→hi (jednosměrně).

**EN-pivot** (auto): pro páry mimo seznam (typicky de→cs, pl→cs, fr→cs,
fr→de) wrapper provede 2 volání ``src→en→tgt`` a vrátí finální překlad
+ warning + ``pivot=True``. Doc-mode v pivotu nepodporován.

Klíčové páry pro legal-tech:
- ``cs-en`` / ``en-cs`` — anglické sumáře, mezinárodní komunikace
- ``doc-cs-en`` / ``doc-en-cs`` (s ``document_mode=True``) — celé dokumenty
  se zachovanou strukturou odstavců
- ``cs-uk`` / ``uk-cs`` — ukrajinští klienti / legal aid pro UA migranty
- ``cs-ru`` / ``ru-cs`` — ruskojazyční klienti
- ``de-cs`` / ``pl-cs`` / ``fr-cs`` — automatický EN-pivot pro EU sousedy

Pozor: SK ↔ CZ pár v Charles Translatoru chybí. SK je auto-alias na CS
(mutual intelligibility). HI lze jen jako tgt (en→hi), ne jako src.

Charles Translator umí vlastní jména zachovat v originále — užitečné
pro legal: *"Jan Vzorek podal žalobu u Krajského soudu v Ostravě."*
→ *"Jan Vzorek filed a lawsuit at the Krajský soud v Ostrava."*

Args:
    text: Text k překladu (UTF-8).
    src: Zdrojový jazyk (default ``cs``).
    tgt: Cílový jazyk (default ``en``).
    document_mode: True pro doc mode (cs↔en only). Zachová strukturu.

Returns:
    ``translated`` (přeložený text), ``src``, ``tgt``, ``pair``
    (skutečně použitý model name), ``document_mode``, ``input_chars``,
    ``output_chars``.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYes
srcNocs
tgtNoen
document_modeNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior4/5

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

No annotations provided, so description carries full burden. It discloses EN-pivot behavior (two calls, warning, pivot flag), document mode constraints, and preservation of proper names. The return structure is described. Mutation aspect is not explicit but translation is inherently non-destructive.

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 description is verbose (over 300 words) with extensive lists and examples. While well-structured with Markdown and headings, it could be shortened without losing essential information. Some detail is redundant for an AI agent.

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?

Given the complexity of language pairs and pivot logic, the description covers all necessary behavioral and constraint details. Output schema exists, so return values are documented separately. Missing an explicit example call, but overall complete.

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

Parameters5/5

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

Input schema has 0% description coverage, so description must compensate. It explains each parameter: 'text' (UTF-8), 'src' (default cs), 'tgt' (default en), and 'document_mode' (only for cs↔en, preserves structure). This adds significant meaning beyond the bare 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 description clearly states the tool translates text using Charles Translator, specifies 8 languages and 17 direct pairs, and distinguishes it from sibling tools like analyze_morphology or anonymize. The verb 'přeloží' (translate) and resource are explicit.

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?

The description provides extensive usage guidance: supported languages, direct vs. pivot pairs, document mode limitations, and key pairs for legal-tech. It implicitly advises when to avoid pivot (no doc-mode) and mentions missing SK↔CZ. However, it doesn't explicitly contrast with sibling tools, though purpose is distinct enough.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Buggy1111/anonymize-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server