Skip to main content
Glama

internationalize

Orchestrates end-to-end i18n migration for React Native, React, Next.js, and Flutter: analyze, scan, plan, apply, translate, and validate with structured reporting.

Instructions

End-to-end orchestration tool for i18n migration across React Native, React (web), Next.js, and Flutter projects. Runs analyze -> scan -> plan -> apply -> translate -> validate with conservative defaults and complete structured reporting.

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": "internationalize"
  }
}

Input Schema

NameRequiredDescriptionDefault
applyNoIf true and dryRun is false, applies source code and locale file modifications.
scopeNoOptional target directories or files to internationalize (e.g. ['src/features/auth']).
apiKeyNoOptional API key for cloud translation provider.
dryRunNoIf true (default), simulates execution, generates plan, and shows diff without modifying files.
excludeNoGlob patterns of files to exclude.
includeNoGlob patterns of files to include.
providerNoOptional translation provider ('auto', 'deepl', 'openai', 'gemini', or 'dictionary'). Defaults to 'auto'.
formalityNoOptional grammatical formality for translations ('formal', 'informal', or 'neutral').
structureNoOptional i18n structure type override ('namespaces', 'nested', or 'flat'). Auto-detected by default.
translateNoIf true and apply is true, translates missing target locale entries using dictionary and glossary.
namespacesNoOptional list of namespaces to limit planning and translation to.
projectPathNoOptional project root directory. Defaults to current working directory.
createBackupNoIf true, creates .bak backup files before modifying any file on disk.
sourceLocaleNoSource locale (e.g. 'en'). Defaults to detected project source locale.
targetLocalesNoTarget locales to internationalize and translate to (e.g. ['fr', 'es']).
failOnWarningsNoIf true, halts and fails if any warning is encountered.
candidateDecisionsNoOptional map of candidate ID (or text) to boolean decision (true = include as user-facing, false = skip as technical) for resolving ambiguous strings.
providedTranslationsNoOptional map of agent-provided translations for target locales (e.g. { fr: { common: { save: 'Enregistrer' } } }).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.6

TDQS

A3.5/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full disclosure burden, and it delivers only partially: it discloses the six-stage pipeline and that defaults are 'conservative', which implies a non-destructive first run. It does not state that nothing is written to disk unless apply is set with dryRun off, that backups are opt-in, that an API key/provider is needed for cloud translation, or anything about runtime cost or reversibility for a tool that can modify source files.

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?

Two tight sentences with zero padding: the first establishes identity and scope, the second front-loads the pipeline stages and the safety posture. Nothing is redundant and the most decision-relevant information comes first.

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

Completeness3/5

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

For an 18-parameter, filesystem-mutating orchestrator with no annotations and no output schema, the description is thin — it gestures at 'complete structured reporting' but does not characterize the result, and it does not explain how the many optional flags combine or what a partial configuration does. It covers the high-level shape adequately but leaves the agent guessing on the operational details that matter most.

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 description coverage is 100% with 18 documented parameters, three enums, and nested objects, so the schema already does the heavy lifting and the baseline is 3. The description adds no parameter-level meaning of its own — the phrase 'conservative defaults' vaguely points at dryRun/apply behavior but never clarifies the interaction between apply, dryRun, translate, and createBackup that an agent must get right.

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?

The description names a concrete action and object — an end-to-end i18n migration orchestrator — and enumerates the exact pipeline stages (analyze -> scan -> plan -> apply -> translate -> validate) plus the supported frameworks (React Native, React, Next.js, Flutter). That makes the tool's identity unambiguous, but it never names a sibling to contrast with, so an agent must infer on its own that the granular tools like analyze_project or translate_i18n are sub-steps of this one.

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?

Use is only implied: 'end-to-end orchestration' suggests reaching for this when you want the whole pipeline rather than one stage, and 'conservative defaults' hints it is safe to try. There is no explicit when-to-use, no when-to-prefer-the-granular-tools guidance, and no stated prerequisites such as needing targetLocales for translation to do anything.

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