Start machine translation for specified keys into target languages. Returns a batch job ID — use get_batch_job_status to poll for completion.
| Name | Required | Description | Default |
|---|---|---|---|
| branch | No | Optional: branch name | |
| keyNames | Yes | Names of keys to translate | |
| namespace | No | Optional: namespace of the keys | |
| projectId | No | ID of the project (required for PAT, auto-resolved for PAK) | |
| targetLanguageTags | Yes | Language tags to translate into (e.g. ['de', 'fr']) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It discloses the asynchronous nature by mentioning a batch job ID and polling. However, it omits potential side effects (e.g., overwriting existing translations), auth requirements, or failure modes, so transparency is incomplete.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences: the first states the purpose efficiently, and the second explains the return value and the next step. There is no fluff, and the structure is front-loaded with the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description at least specifies that the return is a batch job ID and directs to the polling tool. It covers the essential workflow for an async translation trigger. However, it does not mention prerequisites like projectId for PAT (though in schema) or behavior on overlapping keys, making it slightly incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with all five parameters described, so the baseline is 3. The description adds minimal parameter semantics beyond implying 'keys' maps to keyNames and 'target languages' to targetLanguageTags. It does not explain branch, namespace, or projectId, but the schema already does.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Start') and clearly defines the resource and action: 'machine translation for specified keys into target languages'. This distinguishes it from sibling tools like get_translations or set_translation, and the mention of a batch job ID adds operational specificity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear workflow guidance by instructing to 'use get_batch_job_status to poll for completion', which tells the agent what to do after invocation. It implies this tool is for initiating machine translation, not for manual translations, but it does not explicitly list alternatives or exclusion criteria, so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target distinct entities and actions, but a few pairs like create_keys/set_translation and list_keys/search_keys have overlapping functionality. The descriptions clearly differentiate their use cases, so ambiguity is limited.
All tools follow a consistent snake_case verb_noun pattern (create_, delete_, get_, list_, set_, etc.), making the API predictable. The only slight deviation is machine_translate, but it still reads as a single action verb.
With 22 tools, the server covers many aspects of translation management, but the count is slightly above the ideal range. Each tool has a clear purpose, though some could potentially be consolidated without loss of functionality.
The core key and translation lifecycle is well covered, but there are notable gaps: languages only support create and list (no update/delete), tags can be added but not removed, and projects lack get/update/delete operations. These omissions may require workarounds.
