# Fix list: Zoho Desk From Anchor Terminal's listing at https://www.anchorterminal.com/tools/zoho-desk, the October 2026 research run, assessed 8 October 2026. Grade B, 66.6 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 Zoho Desk: 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, 40 out of 100, up to 7.5 more on the total Why it scored 40: No x402, MPP or L402 (0). Edition prices are public, $7 to $40 a user a month billed yearly, and extra API credits have a published rate from $4.20 a month per 1,000 daily credits (20). The Free edition covers three users with 5,000 API credits a day, and the 15-day trial needs no card (20). A person signs up in a browser, registers an OAuth client in the API console and approves scopes (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, 66 out of 100, up to 6 more on the total Why it scored 66: OAuth 2.0 with scopes per module and operation, one-hour access tokens and revocable refresh tokens (30). Less 10 because Zoho's OAuth guide documents the refresh call with the refresh token and client secret in the URL query string as one of three options (20 of 30). READ-only scopes, calls bound by the user's profile permissions, a draft and send-for-review path for replies, and a 60-day recycle bin for deleted tickets. Spam deletion is permanent and no approval step guards bulk updates (15 of 20). Tickets hold customer-written text and no prompt-injection guidance was found (3 of 15). A ticket history endpoint lists actions per ticket and a dashboard shows credit use. A portal-wide audit log for Desk was not established (8 of 15). security.txt valid to 30 June 2028, a bug bounty, SOC 2 Type 2 naming Zoho Desk and ISO/IEC 27001 (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. Agent ergonomics, 67 out of 100, up to 5.4 more on the total Why it scored 67: Graded on the REST API. Lists default to 10 records with at most 50, `include` adds related resources on request, and `fields` exists on some list calls only (18 of 25). `from` and `limit`, saved views, `sortBy` and module search with field filters. Deep offsets cost up to 100 credits a call and search stops at offset 4,999 (18 of 20). Errors carry `errorCode`, `message`, `errorType` and the field as a JSON Pointer (18 of 20). No idempotency key. Drafts can be saved before sending (6 of 20). One official SDK, for Java, and setup needs an hourly token refresh and the right regional host (7 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. Reliability, 75 out of 100, up to 5 more on the total Why it scored 75: Graded on the REST API v1, read as a hosted service. status.zoho.com redirects to us.zohostatus.com, which has a Zoho Desk component (20). The incident history loads by script and we could not read it. The status feed shows the Desk component returning to Operational on 3 September 2026 at the same minute as Zoho CRM, Books, Flow, SalesIQ and Deluge, with no other Desk entry since July, so we read the record as minor incidents only without a duration (20 of 30). Daily credits and concurrency are published with numbers per edition (15). A 429 at the daily limit carries Retry-After, and every response reports credits used and remaining. Concurrency 429s carry no Retry-After, and no idempotency or retry guidance for writes was found (10 of 15). No SLA found, and the Terms of Service disclaim uninterrupted service (0). v1 is the current documented version (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. ## 5. Schema & documentation, 72 out of 100, up to 4.6 more on the total Why it scored 72: zoho/zohodesk-oas on GitHub holds OpenAPI 3.1.0 files for 185 resources and 911 operations (25). No llms.txt at zoho.com or desk.zoho.com and no Markdown docs found (0). 910 of 911 operations carry a description that states the purpose, often with a note on limits, and little on when not to use one (14 of 20). Parameters carry enums, patterns and length limits, and replies use a discriminated schema per channel. Custom fields make record bodies open (12 of 15). The API document has a curl sample and response per endpoint and a list of error codes, and 658 operations declare an error response (14 of 15). The version is in the path and a compatibility statement promises forum notice of changes, with no dated changelog found (7 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. Maintenance & community, 63 out of 100, up to 3.2 more on the total Why it scored 63: The OpenAPI files were last changed on 9 September 2026, 29 days before this check (30). The repository has dated commits on 2, 8 and 9 September 2026, three in the last 90 days, all within one week (20). The developer forum named as the place for API notices loads by script, so replies and dates were unread, and no dated changelog was found (6 of 15). The only official SDK is for Java, version 1.3.0 for Java 7 and above, with no release date found (5 of 15). No public repository or CI for the SDK (2 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. ## 7. Transparency & trust, 79 out of 100, up to 1.8 more on the total Made of editorial 62, provenance 95. Why it scored 79: Closed service under the Zoho Terms of Service, last updated 2 March 2022. The OpenAPI repository has no licence file (15 of 30). The privacy policy of 22 December 2025 says data is deleted from the active database within six months of account termination and from backups three months later. The DPA is sent on request by email (24 of 30). The API document promises forum notice and a transition period for deprecations without stating a length, and marks deprecated fields without dates (8 of 20). A sub-processor page exists, but its directory loads by script and we could not read the list. The data centre page names regions and cities (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): - Terms of service: read, states 6 of the 7 things a reader expects, and has 1 clause that costs points (7.1 of 10) - Privacy policy: read, states 8 of the 8 things a reader expects, and has 1 clause that costs points (8 of 10) ## 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 incident history at us.zohostatus.com/incident_history, which loads by script. The duration and cause of the 3 September 2026 event were not read - unchecked: status pages for data centres other than the US - unchecked: the Zoho Desk Developer APIs forum, which loads by script, so no dated API notice or staff reply was read - unchecked: the sub-processor directory at zoho.com/privacy/sub-processors.html, which loads by script - unchecked: a portal-wide audit log for Zoho Desk. The help centre pages we tried returned articles for other Zoho products - unchecked: Maven coordinates, release date and download counts for the Java SDK, and GitHub stars for the OpenAPI repository - unchecked: Zoho Desk release notes at zoho.com/desk/whats-new.html, which load by script - unchecked: the Zoho contracting entities page, not re-read today - The pricing page showed prices in rupees to our reader. US dollar prices come from the price file the page loads - The webhook document lists an Ultimate edition that the pricing page does not sell. Which editions map to it is not established - Zoho MCP lists Zoho Desk among its apps. Its Desk tools, limits and prices were not found, so the grade covers the REST API only - Whether failed calls and 429 responses use credits is not stated in the reviewed pages - The Terms of Service bar use of the services for competitive or benchmarking purposes, which matters before our probes run - The lead was right on the vendor, URL, docs link and interface ## Weaknesses - No SLA found, and the Terms of Service disclaim uninterrupted service - No dated API changelog. Changes are announced in a community forum that loads by script - No idempotency key on writes, and Retry-After is absent on concurrency 429s - The only official SDK is for Java, version 1.3.0, with no release date or source repository found - Webhooks need Professional or higher. Free and Standard have none - Zoho's OAuth guide documents a refresh call with the client secret in the URL query string ## 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. - Use the `api_domain` returned with the token. Each data centre has its own host, such as desk.zoho.com, desk.zoho.eu and desk.zoho.in - Send `Authorization: Zoho-oauthtoken ` and refresh hourly. Put refresh parameters in the POST body, not the URL - Create replies with `POST /api/v1/tickets/{id}/draftReply`, then `sendDraft` or `sendForReview`. `sendReply` emails the customer - Add internal notes with `POST /api/v1/tickets/{id}/comments` and `isPublic` false - Page with `from` and `limit` (50 at most). Deep offsets cost more credits, from 3 a call under 2,000 records to 100 above 100,000 ## 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.