Call the getAccountLimits MCP tool

Read a LinkedIn account’s daily sending limits (connection requests, messages, reply-agent cap) AND its working-hours ENFORCEMENT state (timezone, per-weekday schedule, enabled flag) in one call. working_hours is the truth every send path actually gates on: if the account has no working-hours row yet, timezone and schedule are null and is_enabled is false, meaning the account is UNRESTRICTED (sends at any hour) - the workers skip the hours gate entirely when there is no row, they do NOT fall back to a 9-5 default. working_hours_source is "configured" when a row exists, "default" when it does not (that "default" behavior IS unrestricted, not a placeholder schedule). When there is no row, working_hours_unset_default separately reports the reference window the UI would create on a first edit (9am-5pm America/New_York) - that window is NOT enforced; use it only as a starting point if you are about to turn working hours ON, never report it as the account’s current hours. limit_source mirrors this for the limits block. Call this before updateAccountLimits’s working_hours_schedule (it requires the full week; read the current schedule here first so you send back all 7 days, not just the one you are changing - or, if working_hours_source is "default", compose any full week yourself, e.g. from working_hours_unset_default). Pass account_id from getLinkedInAccounts.

Called through the Actions bridge: the response is that tool's own result, wrapped as { data: <tool result> } under HTTP 200. Billing, daily-cap, and confirm-step outcomes are embedded INSIDE data, never remapped to an HTTP status (see the templated /api/v1/actions/{toolName} operation above for the full protocol, and x-mcp-actions for this tool's machine-readable scope/cap/confirm_behavior fields). Authentication, request-shape, and optional idempotency-protocol failures still use their documented non-200 statuses.