Skip to main content
Glama
Sign In
@paxalabs/mcp

@paxalabs/mcp

Official
by paxalabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Translate text

translate
Read-onlyIdempotent

Converts text between 15 languages and detects source per segment, so mixed-language input works; accepts one string or up to 200 contextual segments and returns detected languages and review flags.

Instructions

Translate text into any of 15 languages, from any of them, with Paxa Translate: Thai (th), English (en), Chinese (zh), Japanese (ja), Korean (ko), Arabic (ar), French (fr), German (de), Hindi (hi), Indonesian (id), Malay (ms), Portuguese (pt), Russian (ru), Spanish (es), Vietnamese (vi). The source language is detected per segment, so mixed-language text works; a segment already in the target language comes back unchanged. Accepts one string or up to 200 segments that share context, and returns each translation (numbered for segments) with its detected source language, any review flag, and the credits used. For text in a PDF or image, run ocr_document first. Costs 25 credits per 1000 text characters per rendering (minimum 2 credits), so 1000 characters cost 25 credits, or 50 with alternatives 2; instructions, context, examples, do_not_translate strings, and glossary terms bill at 8 per 1000.

Input Schema

NameRequiredDescriptionDefault
textYesText to translate: one string, or an array of segments translated together
formatNoTreat input as plain text, Markdown, or HTML; only the prose of Markdown and HTML is translated, links, code, and tags come back untouched
sourceNoPin the source language only when detection gets it wrong (default "auto", detected per segment). Must differ from target.
targetYesThe language to write, as its code (see the description). Chinese ("zh") is written in Simplified characters.
contextNoBackground that conditions the translation without being translated: the surrounding document, the domain, the audience
examplesNoStyle examples: source sentences with their preferred translations, whose tone and phrasing the translation follows. Up to 100 pairs.
glossaryNoTerm pairs the translation must use, applied in context (inflected and placed grammatically). Send the whole glossary: terms whose source does not appear in the text are dropped before the request runs and never billed.
formalityNo"auto" (default) matches the tone of the source; "formal" writes the target language's polite written register (polite particles in Thai, the polite form of address where a language has one); "casual" writes conversational language between peers.
alternativesNoRenderings per segment, best first (default 1). Each one bills the text again and counts against the 20,000-character text limit.
instructionsNoFree-form direction for the translator: tone, audience, house rules, terminology. Style only.
borrowed_wordsNoHow to render borrowed words: "auto" (default) uses the established form in the target language, "transliterate" writes them in the target script, "preserve" keeps technical terms and proper nouns in their original script
do_not_translateNoStrings that must appear in the translation exactly as written

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.2

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description goes well past them: per-segment language detection, target-language segments returned unchanged, exact credit math (25/1000 chars, 2-credit minimum, alternatives double it, supporting fields at 8/1000), dropped glossary terms are never billed, and the return payload including review flag and credits used.

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?

Front-loaded with purpose, then behavior, then cost — a sensible order with no filler sentences. The one deduction is the inline list of 15 language codes, which duplicates the target enum already in the schema and lengthens the definition without adding selection value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter tool with no output schema, the description still describes the response shape (numbered translations, detected source language, review flag, credits) and explains the cost model, which is the main risk an agent faces when calling it. Nothing needed to call it correctly is missing.

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 billing semantics not present in the schema: alternatives each re-bill the text and count against the character limit, and instructions/context/examples/do_not_translate/glossary bill at 8 per 1000. That materially changes how an agent would size a request.

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?

A concrete verb and resource (translate text) with an explicit scope: 15 named languages, any direction, string or up to 200 segments. It also routes away from a sibling by naming ocr_document for PDF/image input, so an agent can identify this tool without opening the 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 real when-to guidance: pin source 'only when detection gets it wrong', send the whole glossary rather than filtering, run ocr_document first for PDFs/images, and use context/examples for conditioning rather than translating them. It stops short of contrasting with speech siblings like text_to_speech, but the translation-vs-OCR boundary is explicit.

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

Deploy Server

Other Tools