Skip to main content
Glama

create_key

Create translation keys in Texterify to identify i18n strings in your codebase. Configure HTML formatting and pluralization, then populate translations separately.

Instructions

Create a new translation key (i18n string identifier) in the configured Texterify project. This only creates the key entry — it does NOT add any translated content. After creating a key, call set_translation for each language to add translations. Key names must be unique within the project; duplicate names return a validation error with code "TAKEN". Typical workflow: create_key -> list_languages -> set_translation for each language.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_idYesThe Texterify project UUID. You can find this value in the project's texterify.json file under the 'project_id' field
nameYesThe key name used as the i18n identifier in source code, typically in snake_case or dot.notation (e.g., 'welcome_message', 'auth.login.title'). Must be unique within the project
descriptionNoOptional human-readable description to help translators understand the context (e.g., 'Greeting shown on the homepage header'). This is not the translation — it's metadata about where/how the key is used
html_enabledNoSet to true if translation values for this key contain HTML markup. When enabled, the Texterify UI shows a rich text editor for translators. Defaults to false
pluralization_enabledNoSet to true if this key needs plural forms (e.g., '1 item' vs '5 items'). Follows CLDR Plural Rules with forms: zero, one, two, few, many, and other (the content field). When enabled, use the plural parameters in set_translation. Defaults to false
Behavior4/5

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

Adds critical behavioral context beyond annotations: validation error code 'TAKEN' for duplicates, uniqueness constraint within project, and clarification that operation is non-idempotent (matches idempotentHint:false). Annotations cover read/destructive hints; description adds validation behavior and external system interaction context (Texterify project).

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?

Five sentences, each information-dense and necessary: purpose, scope limitation, next-step instruction, validation rule, and workflow. Front-loaded with core action. No redundancy despite covering complex multi-step workflow requirements.

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?

Comprehensive given complexity: covers project_id location (texterify.json), validation constraints, and multi-step workflow. Minor gap: lacks description of return value structure given no output schema exists, though the workflow implication mitigates this.

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 rich descriptions (e.g., CLDR plural rules, snake_case examples). Description does not add parameter-specific meaning beyond the schema, which is acceptable per rubric baseline 3 for high-coverage schemas.

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?

Specific verb 'Create' with resource 'translation key (i18n string identifier)' and scope 'in the configured Texterify project'. Explicitly distinguishes from sibling create_key_with_translations by stating 'it does NOT add any translated content' and from get_key/list_keys by being a creation operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit workflow provided: 'create_key -> list_languages -> set_translation'. Clear when-not-to-use: 'This only creates the key entry'. Names alternative tools for the next step ('call set_translation') and distinguishes this tool's limited scope from complete translation creation.

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/mogharsallah/texterify-mcp'

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