Amazon Location Service

# Fix list: Amazon Location Service

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/amazon-location, the October 2026 research run, assessed 8 October 2026. Grade BB, 74.1 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 Location Service: 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-1,000 prices for every operation and bucket published without a login (20). The pricing page lists monthly allowances for the first three months and up to $200 of credits for new customers, but an AWS account is needed. We did not re-read the sign-up flow today and follow the 1 October reading on the other AWS listings that a card is required (0). A person signs up in a browser. `CreateKey` mints API keys by API only after an account exists (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. Security & auth, 73 out of 100, up to 4.7 more on the total

Why it scored 73: Three credential routes, SigV4 with IAM, Amazon Cognito, and API keys limited to named actions and resources with optional expiry and referrer or app restrictions, which earns 30. Less 10 because the API key is sent in the `key` query parameter, the only documented way to present it (20). API keys reach only read calls on Maps, Places and Routes, and IAM policies scope each action and resource (18 of 20). Results carry place names and third-party map data, and no prompt-injection guidance was found in the reviewed documentation (5 of 15). CloudTrail records management events by default and data events on request, and CloudWatch reports usage by `ApiKeyName` (15). A vulnerability disclosure programme on HackerOne, audit reports in AWS Artifact and a FedRAMP High announcement of 28 October 2024. The security.txt on aws.amazon.com passed its Expires date on 24 September 2026, and no paid bounty was found (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.

## 3. Maintenance & community, 60 out of 100, up to 3.5 more on the total

Why it scored 60: Read as a closed service. The newest API change is in the `geo-maps` model on 17 August 2026 (point-of-interest density and category filters on maps), 52 days before the check (20 of 30). In the last 90 days we found that one model change plus two releases of the agent context package, v1.1.0 on 6 August and v1.2.0 on 11 September 2026. The `geo-places` change of 8 July falls two days outside (10 of 20). AWS What's New posts for the service run to 2 April 2026, re:Post and paid support exist, and the agent context repository had no open issues (10 of 15). Official SDKs are current, `@aws-sdk/client-geo-places` 3.1147.0 on 6 October 2026 and boto3 1.43.109 on 7 October (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.

## 4. Transparency & trust, 70 out of 100, up to 2.6 more on the total

Made of editorial 52, provenance 88.

Why it scored 70: Closed service under the AWS Service Terms, whose section 82 sets out storage, caching and attribution rules in detail (15 of 30). The guide says device positions are kept 30 days, geofences until deleted, and that queries are stripped of customer metadata before they go to data providers. Section 82.1 agrees and adds that providers may process requests outside the chosen region. No retention period was found for Places and Routes requests (20 of 30). Section 82.3 allows AWS to change or drop a provider or feature on notice "where practicable", and no dated deprecation notice or end date for the v1 APIs was found (5 of 20). The data providers (HERE, Esri, GrabMaps and AWS's open data) are named and the region is chosen per request. The AWS sub-processor list was not read today (12 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):

- Terms of service: read, states 6 of the 7 things a reader expects, and has 3 clauses that cost points (3.1 of 10)
- security.txt: published but past its Expires date (5 of 10)

## 5. Schema & documentation, 87 out of 100, up to 2.1 more on the total

Why it scored 87: The Smithy service models for `geo-places`, `geo-routes`, `geo-maps` and `location` (API version 2020-11-19) are public in aws/api-models-aws and in every AWS SDK, a machine-readable contract in the role OpenAPI plays (25). llms.txt for the developer guide, a Markdown twin of each page and the whole guide as `full.md` (10). A choose-an-API page and per-operation pages with use cases say when each call fits, with less on when not to use one (15 of 20). Inputs carry enums and ranges, such as `MaxResults` 1 to 100 and `QueryText` up to 200 characters (15). How-to pages give sample requests, responses, cURL and CLI commands, and each action lists its errors with HTTP codes, but the `ValidationException` fields are documented as "Test stub" (12 of 15). Versioned paths (`/v2/`), yet the document history has one entry, dated 31 October 2024, and changes are announced only in AWS What's New posts (10 of 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. Agent ergonomics, 88 out of 100, up to 2 more on the total

Why it scored 88: API reading of the checklist. Places responses stay at the core fields unless `AdditionalFeatures` asks for more, and `MaxResults` caps the count, but there is no field selection and route responses can reach the 6 MB limit (20 of 25). `MaxResults` on six of seven Places calls, `NextToken` on `SearchText` and `SearchNearby`, and filters by country, bounding box and place type (18 of 20). Four typed errors per API, with a reason and field list on `ValidationException` (17 of 20). Every v2 operation is marked read-only in the model, so retries are safe. No hints apply to a plain API (18 of 20). One required field or none on most calls, an API key that avoids SigV4 signing, and SDKs on npm and PyPI among others (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.

## 7. Reliability, 95 out of 100, up to 1 more on the total

Why it scored 95: Hosted reading. AWS Health Dashboard with a feed per service and region (20). The Amazon Location feeds for us-east-1 and eu-west-1 held no events on 8 October 2026, and the dashboard's event history from 10 July 2026 names no Amazon Location event. The public dashboard lists only broad events, so a clean feed says less than a small vendor's detailed page. The us-east-1 event of 20 October 2025 listed Amazon Location among affected services, outside the 90 days (30). Default rates published per operation, 100 a second for each Places call, 20 for `CalculateRoutes`, 5 for `CalculateRouteMatrix`, with a burst of 80 per cent (15). Throttling returns `ThrottlingException` with HTTP 429, marked retryable in the service model, and every v2 call is a read, but the guide gives no backoff or `Retry-After` guidance (10 of 15). Amazon Location SLA at 99.9 per cent monthly uptime per region (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.

## 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: whether opening an AWS account on the free plan needs a payment card. We did not go through sign-up and scored the free tier as the other AWS listings did on 1 October 2026.
- unchecked: the AWS sub-processor list and the AWS Data Processing Addendum were not read today.
- Prices are those for US East (N. Virginia) in the feed the pricing page loads. Other regions were not compared.
- The What's New listing we read is filtered by AWS's own product tag and may omit posts, such as the Jobs API and address validation launch, whose date we did not establish.
- We read the status feeds for us-east-1 and eu-west-1 only, plus the dashboard's cross-region event history.
- No retention period for Places and Routes request data was found in the reviewed documentation.

## Weaknesses

- The API key is sent as the `key` query parameter, the only documented way to present it
- Storing or caching results is barred unless `IntendedUse` is `Storage`, billed at $4.00 per 1,000 against $0.50 for single use
- An AWS account opened by a person in a browser is needed before any call, and no keyless or machine-payment route exists
- The developer guide gives no backoff or `Retry-After` guidance for `ThrottlingException` (429)
- The guide's document history holds one entry, dated 31 October 2024, so API changes have to be read from the SDK models

## 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.

- Call the v2 endpoints (`places.geo.<region>.amazonaws.com/v2/geocode`, `routes.geo`, `maps.geo`). They need no resource creation, unlike the v1 place index and route calculator calls
- Set `IntendedUse` to `Storage` before saving or caching any Places result. The default `SingleUse` results may not be stored under section 82.4 of the AWS Service Terms
- Read `PricingBucket` in each response. Requesting `Contact`, `Access`, `TimeZone` or `Phonemes` in `AdditionalFeatures` moves a Places call from $0.50 to $1.50 per 1,000
- Keep the API key out of logs and shared URLs, since it travels as `?key=`. Use SigV4 with an IAM role for server-side work, and for the Jobs API, which refuses API keys
- Back off on HTTP 429 `ThrottlingException`. The burst allowance is 80 per cent of the per-second rate within any part of a second

## 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.