AWS End User Messaging

# Fix list: AWS End User Messaging

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/aws-end-user-messaging, the October 2026 research run, assessed 8 October 2026. Grade BB, 74.3 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 AWS End User Messaging: 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, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Per-message prices by country and channel published without login, with a JSON feed for SMS (20). No SMS free allowance. Push is free for the first 1,000,000 notifications a month, and new AWS customers get up to $200 in Free Tier credits. The Free Tier FAQ says most new customers don't need a payment method, though AWS may still ask for one, so half, as on the Amazon SES re-check (10). A person signs up, and production access needs a support case per Region, so no autonomous route (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. Reliability, 73 out of 100, up to 5.4 more on the total

Why it scored 73: AWS Health Dashboard with per-service, per-Region history (20). AWS's dashboard history file, read on 8 October, lists AWS End User Messaging in the Middle East (UAE) me-central-1 and Middle East (Bahrain) me-south-1 multi-service events, open since 1 and 2 March 2026 at disruption status. On 15 September 2026, inside the 90-day window, AWS said it can't restore resources and data hosted only in me-south-1 or the mec1-az2 zone. None of the other eleven events since 10 July names the service. One major event, read as the Amazon SES and S3 re-checks read it (10). Quotas page gives 1 request a second for most actions, the send actions included, and the throughput page gives message parts a second by sender type (15). The API model marks ThrottlingException as retryable and 15 create and request actions take a ClientToken, but the send actions take no idempotency token and we found no backoff guidance in the guide pages we read (8). The AWS User Engagement SLA commits 99.9 per cent monthly uptime per Region and names AWS End User Messaging (10). Generally available (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.

## 3. Agent ergonomics, 71 out of 100, up to 4.7 more on the total

Why it scored 71: No dedicated MCP server. The AWS MCP Server with the aws-sms-voice skill covers guidance and can run the API calls. Send responses return only a MessageId, and 28 list actions take MaxResults (1 to 100) and NextToken (15 of 25). Describe actions take Filters and resource ID lists (16 of 20). Seven typed errors, with reason codes on conflicts (41 values), validation failures (43, plus the failing fields) and quota errors (28) (18 of 20). ClientToken on 15 create and request actions and DryRun on sends, but no idempotency token on SendTextMessage, SendMediaMessage or SendRcsMessage, so a retried send can go out twice (10 of 20). SendTextMessage requires only the destination number, and SDKs exist in every major language, but every call needs SigV4 and a first send needs a registered sender (12 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.

## 4. Security & auth, 88 out of 100, up to 2.1 more on the total

Why it scored 88: IAM with policies per action and resource ARN, service condition keys, temporary credentials and rotation. No secret travels in a URL (30). Policies can allow a single send action on one phone number or pool, and enforced spend limits, protect configurations and deletion protection bound what a credential can do. We found no read-only managed policy for the service and no confirmation step (15 of 20). API responses carry no third-party content. Inbound SMS and RCS go to an SNS topic or Connect Customer, not through API calls (10). CloudTrail logs control-plane calls as management events and the send actions as optional data events, and configuration sets publish per-message events (15). In scope for SOC 1, 2 and 3 (page updated 11 August 2026), with a vulnerability disclosure programme on HackerOne. aws.amazon.com's security.txt expired on 24 September 2026, and we found no paid bug bounty. Read as the Amazon SES re-check read the same evidence (18 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.

## 5. Schema & documentation, 88 out of 100, up to 2 more on the total

Why it scored 88: No OpenAPI, but the Smithy models for both APIs are published in aws/api-models-aws, 110 operations for SMS and Voice v2 and 38 for Social Messaging (25). llms.txt for the user guide and the API reference, with Markdown twins of every page (10). The API reference explains each action, and the guide says when to use Notify and when standard sending. Few actions say when not to use them (12 of 20). 69 enumerated types, length limits and patterns on phone numbers and message bodies, required members marked (14 of 15). The guide carries CLI and Python examples and each action lists its errors, but the SendTextMessage reference page has no examples section (12 of 15). Versioned API (2022-03-31) and a dated document history through 22 September 2026 (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.

## 6. Transparency & trust, 83 out of 100, up to 1.5 more on the total

Made of editorial 70, provenance 95.

Why it scored 83: Closed service under the AWS Customer Agreement and section 29 of the Service Terms, with Apache-2.0 SDKs (20 of 30). The guide says messages are processed and stored in the Region the customer picks and encrypted at rest with service-owned keys, and both the guide and the sub-processor page say downstream carriers may route messages through other regions. We found no retention period for message data (18 of 30). Amazon Pinpoint's end of support on 30 October 2026 carries a dated notice that says these messaging APIs continue, and the document history dates each change. No general deprecation policy found (15 of 20). The sub-processor page, last updated 28 July 2026, names the entities that sell the service and promises 30 days' notice of new ones, but the downstream carriers are not named (17 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)

## 7. Maintenance & community, 85 out of 100, up to 1.3 more on the total

Why it scored 85: The SMS and Voice v2 model last changed on 2 October 2026, and the JavaScript SDK client shipped 3.1147.0 on 6 October (30). Model changes on 31 August, 8 September and 2 October, and guide changes dated 8, 15 and 22 September (20). Closed service with a dated document history and AWS re:Post. Direct support is a paid plan (10 of 15). Official SDKs released on most working days (15). The JavaScript client needs Node 20 or later and is published from the SDK's release pipeline (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.

## 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.

- unchecked: the status of the aws-sms-voice skill in the aws/agent-toolkit-for-aws repository. We read the guide page only and did not clone the repository.
- unchecked: the Social Messaging (WhatsApp) user guide beyond its overview page and API model. Quotas, sandbox rules and inbound handling for WhatsApp were not read.
- unchecked: the service-specific IAM condition keys in the service authorisation reference, which the guide links to.
- No retention period for message content or event data was found in the pages read.
- The pricing page still describes a one-time password check at $0.045 per successful verification, which belongs to the older Amazon Pinpoint API. We did not confirm how it relates to Notify.
- The lead described SMS, MMS and RCS only. The product also covers WhatsApp through a separate API, voice and push.

## Weaknesses

- Sandbox limits new accounts to $1 of SMS a month and ten verified numbers until a support case per Region is approved
- No idempotency token on `SendTextMessage`, `SendMediaMessage` or `SendRcsMessage`, so a retried send can go out twice
- Most actions, the send actions included, default to 1 request a second per account and Region
- No SMS free allowance, and US sending needs a registered 10DLC, toll-free or short code number first
- The AWS Health Dashboard lists the service in the UAE and Bahrain Region disruptions open since March 2026

## 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.

- Sign requests with SigV4 for service `sms-voice` at `sms-voice.<region>.amazonaws.com`. WhatsApp uses a separate API, `social-messaging`
- Check sandbox status and spend limits with `describe-spend-limits` before sending. Sandbox sends reach only verified destination numbers
- Pass `DryRun` on `SendTextMessage` to validate a request without sending, and track `MessageId` yourself because sends take no idempotency token
- Use Notify (`SendNotifyTextMessage`) for one-time passcodes without owning a number. Generate and check the code in your own application
- Read inbound SMS and RCS from the Amazon SNS topic set on the number or pool, and treat message bodies as untrusted text

## 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.