# Fix list: Amazon Translate From Anchor Terminal's listing at https://www.anchorterminal.com/tools/amazon-translate, the October 2026 research run, assessed 1 October 2026. Grade B, 69.8 out of 100. This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public. For a coding agent working on Amazon Translate: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published. ## 1. Payments & pricing, 20 out of 100, up to 10 more on the total Why it scored 20: No x402, MPP or L402 (0). Per-million-character prices for every mode published without a login (20). The pricing page lists 2 million characters a month free for 12 months, but an AWS account needs a card (0). A person signs up in a browser. IAM can mint keys by API only after a human has an account (0). The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments): The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/). - 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which. - 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login. - 20, a free tier or trial that doesn't need a card. - 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API). Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied. Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol. ## 2. Maintenance & community, 25 out of 100, up to 6.6 more on the total Why it scored 25: Read as a closed service. The newest capability in the document history is brevity on 2023-10-31. The service model in aws/api-models-aws changed on 2026-05-21, 2025-10-24 and 2025-08-25, but only in endpoint rules and type casing, with no new operation or parameter (0). No dated service changes in the last 90 days (0). The document history hasn't moved in nearly three years. AWS re:Post and paid support plans exist, SDK issue trackers not checked (5 of 15). Official SDKs current, `@aws-sdk/client-translate` 3.1100.0 on npm and boto3 (15). SDKs regenerate from the model on AWS's release train, CI not checked (5 of 10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance): - 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older. - 20, at least three releases or dated changelog entries in the last 90 days. - 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15. - 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models). - 10, package health, current dependencies and CI. Models are read for deprecation notice periods and model churn rather than release counts. ## 3. Security & auth, 75 out of 100, up to 4.4 more on the total Why it scored 75: Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. SigV4 with IAM users, roles and temporary credentials, scoped per action and resource, and a `TranslateReadOnly` managed policy (30). AWS may store and use text inputs to improve Amazon Translate and other Amazon AI technologies by default. Any customer can opt out with an AI services opt-out policy in `AWS Organizations` (10 of 20). The FAQ says content is stored at rest in the region in use and that some may be stored in another region for service improvement. No zero-retention mode without the opt-out (5 of 15). CloudTrail logs API calls per caller (15). Vulnerability reporting policy, SOC and ISO reports in AWS Artifact and public security bulletins. The security.txt on aws.amazon.com passed its Expires date on 2026-09-24 and we found no public paid bug bounty (15 of 20). The checklist (https://www.anchorterminal.com/benchmark/#checklist-security): - 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option. - 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions. - 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10. - 0 to 15, audit logs or per-call visibility for the operator. - 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public. Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing. ## 4. Agent ergonomics, 80 out of 100, up to 3.3 more on the total Why it scored 80: API reading of the checklist. Responses carry the translation plus `AppliedSettings` and `AppliedTerminologies` and nothing else, and brevity can shorten output, but there's no field selection (20 of 25). List calls page with `NextToken` and `MaxResults`, and request limits are published, but `TranslateText` takes one string, so batching small strings means S3 jobs or many calls (15 of 20). Typed errors an agent can act on, such as `UnsupportedLanguagePairException`, `DetectedLanguageLowConfidenceException` and `TextSizeLimitExceededException` (20). `TranslateText` is stateless and batch jobs take a `ClientToken`. No read-only hints apply to a plain API (15 of 20). Three required fields, `auto` for detection, but SigV4 signing is hard without an SDK. SDKs in every major language (10 of 15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics): - 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries). - 20, pagination, filtering and output-size controls. - 20, actionable, documented error responses, codes and messages an agent can recover from. - 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations. - 15, sensible defaults, few required parameters, and official SDKs in at least two languages. Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs. ## 5. Transparency & trust, 73 out of 100, up to 2.4 more on the total Made of editorial 50, provenance 95. Why it scored 73: Closed service under the AWS Service Terms (15). The FAQ, service terms and opt-out guide agree that AWS may use content by default and that an organisation policy stops it, and a DPA and sub-processor list exist. The same FAQ says AWS will only use content with your consent, which sits awkwardly beside a default you have to switch off (20 of 30). No deprecation policy or dated deprecation notices found for Translate (0). Sub-processors listed and the region chosen per request, but the FAQ allows some content to be stored in another region (15 of 20). The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency): - 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms. - 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors). - 0 to 20, a deprecation policy or notices with dates. - 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted). The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two. Provenance checks not met in full (half of this category, computed from checked facts): - security.txt: published but past its Expires date (5 of 10) ## 6. Reliability, 90 out of 100, up to 2 more on the total Why it scored 90: AWS Health Dashboard with a per-service, per-region RSS feed (20). The Translate us-east-1 feed held no events on 1 October 2026. The public dashboard lists only broad events and account-level ones go to the personal health dashboard, so a clean feed says less than a small vendor's detailed page (30). Quotas published with numbers for batch, terminology and parallel data calls (5 or 10 a second) and for request sizes (10,000 bytes for `TranslateText`, 100,000 bytes for a real-time document), but no rate for `TranslateText` itself, where the guide says the service scales and to contact support (10 of 15). Throttling comes back as `TooManyRequestsException` and `StartTextTranslationJob` takes a `ClientToken` for idempotency, but the Translate guide gives no backoff advice and leaves retries to the SDK defaults (10 of 15). Named in the Amazon Machine Learning Language SLA (10). GA (10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability): Hosted APIs, MCP servers, models and platforms. - 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own). - 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so. - 15, rate limits documented with numbers. - 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved. - 10, an SLA published for any paid tier. - 10, the surface agents use is generally available, not beta or preview. Local packages, SDKs, frameworks and stdio MCP servers. - 20, installs from an official package with supported runtimes stated. - 25, a public CI and test suite, passing on the default branch. - 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered). - 15, semver discipline and breaking changes called out in a changelog. - 15, version 1.0 or later, or declared stable. Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors. ## 7. Schema & documentation, 90 out of 100, up to 1.6 more on the total Why it scored 90: The service model (API version 2017-07-01) is public in every AWS SDK and in the aws/api-models-aws repository, a machine-readable contract in the role OpenAPI plays (25). llms.txt for the developer guide, a Markdown contents page with a link to the whole guide as one Markdown file (10). The guide separates real-time text, real-time documents and S3 batch jobs and says when each fits (15). Inputs typed with enums for formality, profanity and brevity, byte limits and required fields marked (15). Each action lists its errors with HTTP codes, but the API reference has syntax templates and no worked examples (10 of 15). Versioned API and a dated document history (15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema): APIs and MCP servers. - 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool). - 10, llms.txt or Markdown docs served for agents. - 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference. - 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs. - 0 to 15, examples and documented error responses. - 15, versioning and a public changelog. Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference. ## What we couldn't check What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it. - AWS changed its Free Tier for accounts opened from 15 July 2025 to a credit scheme. The Translate pricing page still lists the 12-month allowance and we didn't confirm whether newer accounts get it. - We read only the us-east-1 status feed. - The aws/api-models-aws history starts in May 2025, so changes to the service model in 2024 weren't visible to us. The document history shows none. ## Weaknesses - AWS may store and use text to improve Amazon AI services unless the organisation sets an opt-out policy - No new capability in the document history since 2023-10-31 - 10,000 bytes a `TranslateText` call and one string per call - No published request rate for `TranslateText` - A new AWS account needs a card before the free characters apply ## What costs an agent a turn today The notes we give agents before they call it. Each one is a workaround an agent shouldn't need. - Chunk real-time text under 10,000 bytes, not characters, so multibyte scripts fit less per call - Pass `SourceLanguageCode` auto to detect the source language, and handle `DetectedLanguageLowConfidenceException` - Read `AppliedSettings` in the response, since unsupported formality or profanity settings are dropped without an error - Retry `TooManyRequestsException` with backoff, which the AWS SDKs do by default - Set the AI services opt-out policy before sending private text ## What the review panel asked for - Confirm the new-account allowance - State failed-call billing - error on unsupported settings ## When it's done Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.