Multilocale

Add key with translations

add_phrase

Destructive

Create a new key in a project’s default locale and generate translations for every other configured locale. Omit value to use the key as its source value. Refuses to overwrite an existing key.

Input Schema

TableJSON Schema

Name	Required	Description
`key`	Yes	New exact phrase key
`model`	No	Translation model to use. Defaults to gpt-5.6-luna.
`value`	No	Source value in the default locale. Omit to use the key itself.
`context`	No	Optional context that helps translators disambiguate the phrase.
`project`	Yes	Project name (slug) to add the key to

Output Schema

TableJSON Schema

Name	Required	Description	Default
`key`	Yes
`status`	Yes
`locales`	Yes
`project`	Yes
`defaultLocale`	Yes
`translationCount`	Yes

TDQS

A3.5/5.0

Behavior1/5

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

The description states 'Refuses to overwrite an existing key,' which indicates a non-destructive create-and-translate operation, while annotations set destructiveHint=true. This is a direct annotation contradiction and seriously misleads an agent about side effects. The additional translation-generation and value-fallback details are helpful, but the conflict dominates.

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?

Three sentences carry purpose, fallback behavior, and overwrite protection with no filler. The most important behavioral facts are front-loaded.

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?

Output schema exists and parameters are well documented, and the description covers the core create-and-translate behavior. However, the destructiveHint contradiction leaves the safety model ambiguous, and the description does not clarify failure behavior or what happens when translation generation encounters issues, so it is not fully complete.

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%, so every parameter already has a clear type and semantic description. The description reinforces the value-omission behavior, but that is also present in the value property's schema, so it adds no significant new parameter-level meaning.

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 states a concrete action: 'Create a new key in a project's default locale and generate translations for every other configured locale.' This distinguishes add_phrase from sibling tools like update_phrase, delete_phrase, and read-only phrase lookup tools.

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 clearly frames the tool as the creation path for new keys and warns 'Refuses to overwrite an existing key,' implying agents should not attempt edits here. It does not explicitly name update_phrase as the alternative for existing keys, so it stops short of a full 5.

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

All Multilocale tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation3/5

Most tools have distinct purposes, but several overlap: get_project and show_project_overview both fetch a project by id/name, and list_phrases, search_phrases, and export_locale_dictionary all return phrase collections in similar ways. Descriptions help clarify edge cases, but an agent could plausibly select the wrong tool in several scenarios.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern: add_, delete_, get_, list_, search_, find_, update_, export_, share_, show_. Minor differences like get_project vs show_project_overview do not break the overall naming convention.

Tool Count4/5

17 tools is slightly above the ideal range but still reasonable for a localization server covering projects, locales, phrases, translation searches, sharing, and team roster. Each tool represents a real operation, even if a few could be consolidated.

Completeness4/5

The surface covers core project and phrase lifecycles well: create/read/update for projects and phrases, delete for phrases, locale updates, translation generation, search/export, and missing-translation analysis. Minor gaps exist, such as no delete_project, no explicit unshare_phrase operation, and no dedicated remove_locale tool.

Resources

Need Help?