Global Eglobal-e.com
Global E's API contract and discoverability are strong — partners and agents can find and read the surface without friction. The critical gaps are in operational reliability and agent readiness: there is no sandbox environment, no idempotency or rate-limit guidance, no runnable examples, and no agent instruction file, meaning partners and their AI agents are forced to experiment directly against production with no safety net and no reliable context to build from.
API DesignA clean, typed, well-governed API contract agents can reason about3 pass2 warn0 fail92A+
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Auth declared & discoverablevia spec | 25/25 | authentication is documented on the docs site at https://docs.global-e.com/authentication, even though it isn't declared in the API spec. Investigated: spec 100%, docs 100%. | Agents can only call an API when they can determine its auth posture — a declared scheme, or an explicit statement that none is required. |
| warn | Schema coverage & depthvia spec | 22.2/25 | The request body of POST /checkout/CreateOrder has a structured shape (more than 5 top-level fields, or a nested object / array-of-objects field), which is harder for an agent to fill correctly. Investigated: spec 89%. Fix: Flatten the request body, or document each field's shape with a worked example. | Typed, complete request/response schemas are what make agent function-calling possible. |
| warn | Machine-readable, versioned contractvia spec | 18.8/25 | The API sets a version ("1.0.0") but exposes no versioning scheme in the URL, a header, or the media type, so an agent can't pin to a specific version. Investigated: spec 75%, docs 50%. Fix: Pick a versioning scheme (URL path /v1/, Accept: application/vnd.x+json, or a version header) and apply it consistently. | A current OpenAPI version with a declared versioning scheme lets agents reason about the contract. |
| pass | Security & governance hygienevia spec | 15/15 | No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 0%. | No leaked secrets, no critical lint violations, no OWASP API Top-10 spec smells, and a published vulnerability-disclosure channel. |
| pass | Example coveragevia spec | 10/10 | Only 50% of parameters and responses (1 of 2) include examples (target 80%+), so an agent guesses payload shapes the schema under-specifies. Investigated: spec 100%, docs 0%. | Examples carry shape semantics schemas under-specify — for humans and agents alike. |
Developer ExperienceThe context both developers and agents need to integrate fast — onboarding, code samples, complete descriptions and worked examples2 pass1 warn2 fail65C
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Self-service developer portalvia docs | 29/29 | Signup page found at https://www.global-e.com/join-us/, but no free tier or sandbox is documented in docs/pricing, so an agent may hit a paywall. Investigated: docs 100%. | A first call without a human in the loop — self-serve credentials, a free tier, or an API that needs none. |
| pass | Description completenessvia spec | 15/15 | 100% of operations and parameters carry substantive descriptions (1 of 1 ops, 0 of 0 params), the main semantic cue an agent relies on. Investigated: spec 100%. | Complete descriptions are the context humans and agents need to use endpoints. |
| warn | Quickstart presentvia docs | 12.5/25 | Quickstart page is reachable at https://docs.global-e.com/getting-started (1 variants scanned) but has no runnable code sample in its HTML or .md variant, so there's nothing to copy and run. Investigated: docs 50%. Fix: Add a copy-pasteable curl or SDK call, with the expected response, to the quickstart page (or its .md variant). | A quickstart is the fastest path from landing page to first successful call. |
| fail | Code samples in docsvia docs | 0/18 | No code samples detected across 20 sampled docs pages, so a coding agent gets no ready-to-use examples. Investigated: docs 0%. Fix: Add copy-pasteable code samples to API reference and quickstart pages. | Multi-language samples shorten time-to-first-call. |
| fail | Changelog publishedvia spec | 0/13 | No changelog link or mention appears in the spec, so an agent can't tell what changed before something breaks. Investigated: spec 0%, docs 0%. Fix: Publish a structured changelog (e.g., /changelog.json or releases.atom) and reference it in info or externalDocs. | A published changelog lets partners track changes without surprise. |
Agent DiscoveryPartners and their agents can find your APIs — llms.txt, registries, crawlable and reachable docs3 pass1 warn0 fail91A+
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Docs reachable, not hard auth-gatedvia docs | 30/30 | All 1 pages are publicly accessible. Investigated: docs 100%. | Agents can only index and fetch docs they can reach — past auth gates and over correct HTTP semantics. |
| pass | Registry & SDK presencevia docs | 28/28 | Indexed on Context7 (websites/global-e_enterprise_en, 3434 snippets). Investigated: docs 100%, sdk 0%, cli 0%. | Listing in MCP registries and publishing SDKs puts the API where agents and their tooling look. |
| warn | llms.txt present, valid & comprehensivevia docs | 19.5/30 | No llms-full.txt was found at any candidate origin, so agents can't grab your full docs in one fetch. Investigated: docs 65%. Fix: Publish a concatenated, agent-readable copy of your documentation at /llms-full.txt on your docs site. | A valid, comprehensive llms.txt is the machine-readable entry point for agents. |
| pass | Crawlable / AEOvia wellknown | 12/12 | robots.txt lets all monitored AI crawlers reach the docs paths. Investigated: wellknown 100%. | Bots allowed plus a fresh sitemap make docs findable by agent crawlers. |
Agent UnderstandingAgents can correctly interpret your APIs — machine-readable errors, consistent descriptions, structured data, parseable docs2 pass3 warn1 fail63C
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Agent-navigable, token-efficient docsvia docs | 22/22 | All 1 pages contain server-rendered content. Investigated: docs 100%. | Server-rendered, clean, small-footprint docs are what an agent can cheaply fetch and parse correctly. |
| warn | Operation purpose clarityvia spec | 16.7/25 | Only 0% of operations (0 of 1) have a clear summary plus descriptive name, so an agent must guess purpose from the URL path for most. Investigated: spec 67%. Fix: Operations without a summary or operationId force agents to guess purpose from the path. Add a concise summary + descriptive operationId to each. | Agents select the right endpoint from its summary + operationId; clear, named operations make tool-selection reliable — the strongest driver of correct tool choice. |
| pass | Docs structured datavia docs | 8/8 | Machine-readable JSON-LD Article markup on 20 of 20 assessed pages (100%), with dateModified present. Investigated: docs 100%. | Structured data (JSON-LD/schema.org) on docs pages gives agents an unambiguous parse target and is what answer engines cite. Detected on the JS-rendered head (Firecrawl) for a bounded page budget, so JS-injected JSON-LD is now caught; pages we can't render are excluded rather than failed. |
| warn | Machine-readable errors (RFC 9457)via spec | 4.7/28 | No error responses (4xx/5xx or a catch-all default) are documented anywhere in the spec, so an agent can't anticipate or handle failures. Investigated: spec 17%, docs 17%. Fix: Document at least the common error codes (400, 401, 403, 404, 429, 500) per operation. | RFC 9457 problem details and a documented error-code inventory let agents parse failures without burning tokens. |
| warn | Description consistency across surfaces | 2.1/7 | Mean pairwise description similarity across 2 surfaces (spec, docs) is 11% (threshold 35% for full credit). Fix: Align the API description across spec, docs, and SDK so an agent reading any one surface gets the same story. | Every surface tells the same story about what the product is. |
| fail | Agent instructions file (AGENTS.md)via wellknown | 0/10 | No AGENTS.md at the site root or /.well-known/, so coding agents have no ready-made setup and usage instructions. Investigated: wellknown 0%. Fix: Publish an AGENTS.md with setup, auth, and usage instructions a coding agent can follow. | An AGENTS.md gives coding agents explicit setup, auth, and usage instructions to interpret and operate the API — beyond llms.txt's link index. |
Agent UsabilityAgents have the context to use your APIs reliably, not just find them0 pass0 warn4 fail40F
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| fail | Idempotency documentedvia spec | 0/27 | Only 0% of mutating operations (0 of 1) document idempotency, so an agent's retries can create duplicate writes. Investigated: spec 0%, docs 0%. Fix: Agents retry on failure; without idempotency, retries create duplicates. Document Idempotency-Key on every POST/PUT/PATCH/DELETE. | Documented idempotency lets agents retry safely. |
| fail | Rate-limit signalingvia spec | 0/22 | No rate-limit response headers are documented, so an agent can't tell when it is approaching a limit and will get throttled. Investigated: spec 0%, docs 0%. Fix: Add x-ratelimit-* response headers and document retry-after semantics. | Machine-readable rate-limit headers let agents throttle adaptively. |
| fail | Sandbox separationvia spec | 0/20 | None of the 1 declared server(s) is a sandbox/test host, and no test-key prefixes are documented, so agents can only hit production. Investigated: spec 0%, docs 0%. Fix: Add a sandbox server in spec.servers[] with visually distinguishable test credentials. | An isolated environment lets agents exercise destructive operations safely. |
| fail | Runnable collection with test scriptsvia platform | 0/9 | No public Postman workspace found for the org, so there's no runnable collection an agent can execute against. Investigated: platform 0%. Fix: Publish at least one public Postman workspace and link it from your developer portal so agents can use Run-in-Postman. | A public, maintained collection with assertions is runnable truth agents validate against. |
| na | Pagination documented & consistent | —/22 | No surface produced evidence for this capability in this run. | Consistent, documented pagination lets agents traverse collections. |
Resources Discovered
The public resources we found for Global E — the evidence behind the score. All discovered from public sources; nothing here requires access to your systems.
| Agent hints | Context7 (3,434) |
|---|---|
| APIs analyzed | 3 — CreateOrder, DispatchOrders, GetCatalogPrices |