Store translations. Money is integer minor units (cents). Calling this changes nothing: it returns a preview of what would change and a confirmation link. Only the merchant, on that page, can make it happen.
| Name | Required | Description | Default |
|---|---|---|---|
| locale | Yes | The language the values are written in, as the shop offers it: pt, de, pt-BR. Never the shop's own language. | |
| entries | Yes | Every field translated in this batch. One call per batch, not one per field. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without relying on annotations, the description discloses the crucial behavior: the call returns a preview of what would change plus a confirmation link, and nothing is committed until the merchant confirms. This goes well beyond the structured hints and is exactly the kind of staging/authorization semantics an agent needs. The annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) are consistent with this staged-write model.
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 behavioral sentences are front-loaded and earn their place, but the second sentence ("Money is integer minor units (cents)") is unrelated to translations and is likely boilerplate copied from a pricing tool, which wastes attention and risks confusing the agent. Otherwise the text is tight.
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?
With no output schema, the description usefully characterizes the return value (a preview of changes plus a confirmation link) and the authorization flow, which is the most important missing piece. It stops short of describing the shape of the preview payload or what happens to a batch of up to 200 entries, and the stray money sentence is noise rather than completeness.
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 description coverage is 100%, and the schema itself is unusually rich (locale, entity enum, field key formats, handle vs id, value HTML semantics), so the baseline of 3 applies. The description adds no parameter-level meaning; the one detail it offers (money in minor units) is irrelevant to this tool.
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 names a specific verb+resource ("Store translations") and immediately qualifies it as a preview-only staging operation. It clearly distinguishes this from translations_missing, which the schema references for discovering keys, though the description itself does not name that sibling. The opening phrase is slightly at odds with the preview semantics, but an agent can still tell what the tool does.
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?
It states the key usage fact — that calling it does not apply changes and that only the merchant can confirm — which is important context. However, there is no explicit guidance on when to prefer this over editing content directly, nor a pointer to run translations_missing first to obtain valid keys (that dependency is only implied by the schema).
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.
