# Fix list: Square Appointments (Bookings API) From Anchor Terminal's listing at https://www.anchorterminal.com/tools/square-appointments, the October 2026 research run, assessed 14 October 2026. Grade B, 68.1 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 Square Appointments (Bookings API): 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. Reliability, 55 out of 100, up to 9 more on the total Why it scored 55: Graded on the hosted Bookings API, part of Square's REST API. Status page at issquareup.com with an incident history (20). In the 90 days to 14 October 2026 it lists 15 incidents, all labelled minor, including widespread elevated latency and errors across Square on 27 September that closed after 1 hour 47 minutes. None names Appointments or bookings (10). No numeric limits were found for the REST API (0). The docs describe 429 `RATE_LIMITED`, exponential backoff with jitter, and `idempotency_key` on CreateBooking, UpdateBooking and CancelBooking (15). No SLA found (0). All 24 Bookings and Booking Custom Attributes operations are marked PUBLIC in the 2026-09-16 spec. The MCP server is beta (10). Total 55. 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. ## 2. Payments & pricing, 40 out of 100, up to 7.5 more on the total Why it scored 40: No x402, MPP or L402 (0). Prices are public without login. Square Free is $0 a month per location, Plus $49 and Premium $149, and the comparison table lists the Bookings API under Plus and Premium (20). The sandbox is free, and buyer-level bookings work on the free Appointments plan (20). A person creates a Square account and a Developer Console application, or approves OAuth in a browser (0). Total 40. 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. ## 3. Security & auth, 70 out of 100, up to 5.3 more on the total Why it scored 70: OAuth with read and write scopes for appointments (`APPOINTMENTS_READ`, `APPOINTMENTS_WRITE`, `APPOINTMENTS_ALL_READ`, `APPOINTMENTS_ALL_WRITE`, `APPOINTMENTS_BUSINESS_SETTINGS_READ`), 30-day access tokens, refresh and revocation. Personal access tokens are unrestricted (26). Buyer-level permissions confine an app to the bookings it created, and read scopes exist. No confirmation step for cancellation (15). Booking notes and customer notes are free text. No prompt-injection guidance found (3). API Logs keep each request for 28 days (12). Bugcrowd programme linked from the security page, ISO 27001 and PCI stated, no security.txt (14). Total 70. 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: ListBookings takes `limit` and a cursor, and SearchAvailability takes a time range and segment filters. No field selection outside GraphQL (18). Cursor pagination, filters by location, team member and customer, and bulk retrieve (18). Errors carry a category, a code and the field at fault (18). `idempotency_key` on create, update and cancel, and `booking_version` for optimistic locking. The MCP tools carry no readOnlyHint or destructiveHint annotations (15). Seven official SDKs. A booking needs the location, a bookable team member, a service variation ID and version and a customer, each fetched from another API first (11). Total 80. 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, 70 out of 100, up to 2.6 more on the total Made of editorial 56, provenance 84. Why it scored 70: Closed service under the Square Developer Terms (updated 10 September 2026). The API spec and MCP server are Apache 2.0 (15). The privacy notice of 15 September 2026 gives no retention periods, and no public DPA was found (13). APIs are typically retired at least 12 months after deprecation, with dated notices (20). Service providers by category, processing in the US, Japan, the UK and the EU, no named list (8). Total 56, matching the Square listing, which shares these documents. 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 2 clauses that cost points (5.1 of 10) - Privacy policy: read, states 7 of the 8 things a reader expects (9.3 of 10) - security.txt: not found (0 of 10) ## 6. Maintenance & community, 71 out of 100, up to 2.5 more on the total Why it scored 71: Square released API version 2026-09-16 on 16 September 2026, and the Bookings API is served under it. The changelog index shows no Bookings change since 19 September 2024 (customer address on bookings), so we depart from the 30 for a release within 30 days and give 20. Three dated Square releases in 90 days, 15 July, 19 August and 16 September 2026 (20). Release notes, a developer forum and a Discord community (10). Seven official SDKs regenerated for 2026-09-16, and the MCP server includes `bookings` and `bookingcustomattributes` services, though it is not in the official MCP registry (15). The npm package square-mcp-server is still 0.1.2 from April 2025 (6). Total 71. 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. ## 7. Schema & documentation, 89 out of 100, up to 1.8 more on the total Why it scored 89: Public OpenAPI 3.0 spec in square/connect-api-specification covering all 24 booking operations (25). developer.squareup.com/llms.txt indexes the docs, and guide pages answer in Markdown with `.md` (10). Operation descriptions state purpose, and the guides explain seller-level and buyer-level access and what fails without a paid plan (15). Booking request schemas are typed with required fields and enums for status and location type (13). Guides carry request and response examples and the 403 body returned when a seller's plan doesn't allow writes. Errors share Square's category, code and detail format (11). Dated API versions set by `Square-Version` and monthly release notes (15). Total 89. 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. - The pricing table lists the Bookings API under Plus and Premium only, while the developer docs say buyer-level access works for every seller, including the free plan. Both are recorded - No numeric REST rate limits and no SLA were found in the reviewed documentation - unchecked: the remote MCP server's live tool list, which needs OAuth. The bookings service is read from the open-source server - unchecked: the trial length for Plus and Premium, which the pricing page renders with JavaScript - Square is listed separately as `square` in commerce. This listing covers only the Bookings API and Square Appointments ## Weaknesses - Seller-level create, update and cancel fail with 403 unless the seller pays for Plus ($49) or Premium ($149) per location - Services with a non-zero no-show fee cannot be booked through the API, and the fee can't be set through it - No Bookings API change in the changelog since 19 September 2024 - No numeric REST rate limits or SLA were found - Bookable team members can only be set in the Square Dashboard ## 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. - Act for the seller. This API books into one Square seller's calendar, not across businesses - Call RetrieveBusinessBookingProfile and check `support_seller_level_writes` before trying to create or cancel a seller-level booking - Call SearchAvailability first, then CreateBooking with the service variation ID and version, team member, location and customer - Send a fresh `idempotency_key` on each create, update or cancel, and pass `booking_version` when cancelling - Check `no_show_fee` on the service. A service with a non-zero fee must be booked by the customer elsewhere ## 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.