Skip to main content
Glama

Localize chosen listing

optimizer_localize

Creates per-locale listing drafts by translating core phrases and measuring local phrasings in each locale's test market, then writes a localized description from the winners. Locales run as a background job.

Instructions

Write per-locale drafts of the chosen listing: the core phrases are translated, candidate local phrasings are measured in each locale's test market, and the best are used. Each language not in the main language also gets its own full description, translated from the description that will be published (the Copy draft when it is set to publish, else the live one) around its local phrases (skipped with a note when it fails); variants of the main language (en-GB for en-US) take a new main description as written. Fields edited with optimizer_edit_locale are kept unless redoEdited is true. A locale that fails does not stop the others; get_optimizer lists failedLocales and lastError. Background job.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "projectId": "<projectId>"
    },
    "name": "optimizer_localize"
  }
}

Input Schema

NameRequiredDescriptionDefault
scopeNoWithout locales: the tracked markets' locales (markets, default) or every listing locale of the store in fast mode (all: batched AI candidates, parallel, measured in each locale's test market only).
localesNoOnly these locales (default: see scope).
projectIdYesProject id (from get_overview).
remainingNoOnly locales without a draft yet or that failed last time (finish an interrupted run).
directionsNoOptional creative direction for the AI, e.g. "emphasise offline use".
redoEditedNoRewrite fields the owner edited too (default: they are kept).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.3
    • addedInput schema / properties / redoEdited
      Added value: +{
      +  "description": "Rewrite fields the owner edited too (default: they are kept).",
      +  "type": "boolean"
      +}
  2. First observedv0.1.7

TDQS

A4.1/5.0
Behavior4/5

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

Goes well beyond the annotations: it discloses that this is a background job, that per-locale failures are isolated ('A locale that fails does not stop the others'), where failures surface (get_optimizer's failedLocales and lastError), how edited fields survive unless redoEdited is set, and that main-language variants (en-GB for en-US) take a new main description as written. These are exactly the side effects and failure semantics the annotations (destructiveHint=false, idempotentHint=false) cannot convey; the only gap is polling/completion behavior for the background job.

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 the purpose sentence, then progressively narrower detail. It is one dense paragraph with multiple parentheticals and a final sentence fragment ('Background job.'), which is slightly clipped but every clause carries substantive information about defaults or failure handling.

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?

With no output schema, the description compensates by pointing to get_optimizer for failedLocales and lastError and by flagging the async nature of the run. Coverage of the mutation surface, translation source, and edit preservation is thorough; only the mechanics of waiting for or confirming a background job's completion are underspecified.

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 description coverage is 100%, so the baseline is 3, but the description earns more by explaining the interaction behind redoEdited (rewrite fields the owner edited in optimizer_edit_locale) and by tying the translation source to publish state ('the Copy draft when it is set to publish, else the live one'). scope and remaining are left largely to their schema text.

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?

States a specific verb and resource ('Write per-locale drafts of the chosen listing') and immediately explains the mechanism: core phrases translated, local phrasings measured per test market, best ones kept. It also carves itself apart from optimizer_edit_locale by declaring that fields edited there are preserved unless redoEdited is true, so an agent can distinguish the two tools without opening schemas.

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?

Usage is implied rather than stated: 'the chosen listing' signals a prior optimizer_choose step, and 'finish an interrupted run' via remaining gives a concrete follow-up scenario. However there is no explicit when-to-use/when-not framing, no stated prerequisites, and no routing against siblings such as localize_keyword, leaving the agent to infer the position in the workflow.

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