> ## Documentation Index > Fetch the complete documentation index at: https://docs.getsales.io/llms.txt > Use this file to discover all available pages before exploring further. # Compose agent scenario > Compose a scenario draft from what the person said: a new scenario of the team's own, or with sid a change to it, the unmentioned kept. Nothing is saved: the draft comes back to edit and save through create_agent_scenario or update_agent_scenario (platform_key names a platform scenario it recognized: edit that one). result.notes says what it still needs. 503 composer_unavailable; 422 compose_invalid (outside the vocabulary); 404 when sid names no scenario. Contract: - MCP tool `compose_agent_scenario`, registry package `mcp.unibox/agent_scenarios`, mount `unibox.agent`. - Operation `action`, response envelope `action`. - Flags: read only. ## OpenAPI ````yaml /api-reference/unibox/openapi.yaml post /api/agent-scenarios/compose openapi: 3.0.3 info: title: 'GetSales public contract: gs.service.unibox' description: >- The team inbox and the AI SDR: every LinkedIn and email thread in one place (conversations, messages, the timeline events), the manual tasks a thread spawns, the sender profiles the team speaks through with their LinkedIn account and mailboxes, and the one agent per team with its scenarios, plans and runs. GENERATED. This document is projected from the Zod MCP tool registry in `product/mcp/gs.mcp` (one tool per public endpoint, 1:1). Do not edit it by hand; edit the tool definition and regenerate with `pnpm openapi:public`. Surface: the public `/api` contract of `gs.service.unibox`, 125 operations. This is the only OpenAPI document the platform publishes. Internal (`/internal`) and health endpoints are deliberately absent: they are not part of any contract, they can change without notice, and the service source is their only description. Conventions: - Auth is a bearer JWT, optionally narrowed by the `Team-SID` header. - Every success body is an MCP envelope: `success: true` plus one typed `operation` shape (`search`, `get`, `create`, `update`, `delete`, `metrics`, `group_by`, `action`), and a `meta` block with `trace_id` for support. - Every failure is the same `McpError` envelope with a code from a fixed 16-code taxonomy, so a client maps errors once. - Lists page with `page_size` (0 to 500, default 50) plus an opaque forward `cursor`; `page_size: 0` returns counts only. - On `GET` and `DELETE`, object-valued query parameters (`filter`, `sort`) travel as JSON text and array-valued ones repeat as `name[]=value`. - The MCP-only `_meta` field (usage analytics) never reaches the backend and is not part of this contract. version: '1.0' contact: name: GetSales url: https://getsales.io email: support@getsales.io license: name: Proprietary url: https://getsales.io/terms servers: - url: https://beta.getsales.io/unibox/v1 description: >- Production (the gateway path on the beta ring; the origin is provisioned per DEPLOY_MAP.md) security: - BearerJwt: [] TeamSid: [] tags: - name: agent_answers description: >- Registry package `mcp.unibox/agent_answers`, served on MCP mount `unibox.knowledge`. - name: agent_conversation_uploads description: >- Registry package `mcp.unibox/agent_conversation_uploads`, served on MCP mount `unibox.agent-memory`. - name: agent_examples description: >- Registry package `mcp.unibox/agent_examples`, served on MCP mount `unibox.agent-memory`. - name: agent_hints description: >- Registry package `mcp.unibox/agent_hints`, served on MCP mount `unibox.agent-memory`. - name: agent_plans description: >- Registry package `mcp.unibox/agent_plans`, served on MCP mount `unibox.agent`. - name: agent_runs description: >- Registry package `mcp.unibox/agent_runs`, served on MCP mount `unibox.agent-memory`. - name: agent_scenarios description: >- Registry package `mcp.unibox/agent_scenarios`, served on MCP mount `unibox.agent`. - name: agent_source_parses description: >- Registry package `mcp.unibox/agent_source_parses`, served on MCP mount `unibox.knowledge`. - name: agent_sources description: >- Registry package `mcp.unibox/agent_sources`, served on MCP mount `unibox.knowledge`. - name: agent_tests description: >- Registry package `mcp.unibox/agent_tests`, served on MCP mount `unibox.agent-memory`. - name: agents description: >- Registry package `mcp.unibox/agents`, served on MCP mount `unibox.website`. - name: conversation_events description: >- Registry package `mcp.unibox/conversation_events`, served on MCP mount `unibox.inbox`. - name: conversations description: >- Registry package `mcp.unibox/conversations`, served on MCP mount `unibox.inbox`. - name: messages description: >- Registry package `mcp.unibox/messages`, served on MCP mount `unibox.inbox`. - name: sender_profiles description: >- Registry package `mcp.unibox/sender_profiles`, served on MCP mount `unibox.sender-profiles`. - name: tasks description: Registry package `mcp.unibox/tasks`, served on MCP mount `unibox.inbox`. - name: timeline description: >- Registry package `mcp.unibox/timeline`, served on MCP mount `unibox.inbox`. paths: /api/agent-scenarios/compose: post: tags: - agent_scenarios summary: Compose agent scenario description: >- Compose a scenario draft from what the person said: a new scenario of the team's own, or with sid a change to it, the unmentioned kept. Nothing is saved: the draft comes back to edit and save through create_agent_scenario or update_agent_scenario (platform_key names a platform scenario it recognized: edit that one). result.notes says what it still needs. 503 composer_unavailable; 422 compose_invalid (outside the vocabulary); 404 when sid names no scenario. Contract: - MCP tool `compose_agent_scenario`, registry package `mcp.unibox/agent_scenarios`, mount `unibox.agent`. - Operation `action`, response envelope `action`. - Flags: read only. operationId: compose_agent_scenario requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ComposeAgentScenarioRequest' responses: '200': description: '`action` success envelope.' content: application/json: schema: $ref: '#/components/schemas/ComposeAgentScenarioResponse' 4XX: $ref: '#/components/responses/McpClientError' 5XX: $ref: '#/components/responses/McpServerError' components: schemas: ComposeAgentScenarioRequest: type: object description: Request body of `compose_agent_scenario`. properties: agent_sid: type: string minLength: 18 maxLength: 18 pattern: ^ub_ag_ description: >- The AI SDR whose scenario it is (ub_ag_…); with a platform key, which agent's version. Left out, the team's default agent. text: type: string minLength: 1 maxLength: 8192 description: What the person said, as they said it. sid: type: string minLength: 1 maxLength: 64 description: The scenario the words change; leave it out for a new scenario. required: - text ComposeAgentScenarioResponse: type: object properties: success: type: boolean enum: - true operation: type: string enum: - action action: type: string description: kebab-case verb; matches the route segment. item: {} result: type: object properties: draft: type: object properties: title: type: string nullable: true description: >- A new scenario of the team's own: its name. A change to a platform scenario: null (the name is the platform's). trigger: type: string nullable: true description: >- A new scenario: when it applies, in the words a reply would use (the classify reads it). A change to a platform scenario: null. goal: type: string description: 'One line: what the scenario is for.' steps: type: array items: type: object properties: id: type: string minLength: 1 maxLength: 32 description: >- Stable inside the playbook (react, stage, reply, wait, followup, last_wait, task on the platform seeds); minted for an added step. kind: type: string enum: - react - move_stage - like_post - send_message - wait_for_reply - wait_until - create_task - find_people - reach_objective - use_playbook - resume_orchestration - stoplist_person enabled: type: boolean description: 'Off: never planned under this scenario.' locked: type: boolean description: >- Platform only: the step cannot be switched off, moved or removed (the stoplist step of do_not_contact). when: type: string nullable: true maxLength: 512 description: >- "Plan it when ...": the condition the planning turn judges; null = always. instructions: type: string nullable: true maxLength: 2048 description: >- What the step must do or say, the text the model reads; the product copy a team reads IS the prompt text. params: type: object additionalProperties: {} description: >- The kind's product parameters, each a value of its dictionary (see above). required: - id - kind - enabled - locked - when - instructions - params description: >- The steps in order, as create or update takes them: every param a value of its dictionary, the defaults filled, enabled and locked set. instructions: type: string nullable: true description: The team's words over every step; null when there are none. level: type: string enum: - autopilot - copilot - conditional - 'off' description: >- The level the draft keeps or sets: off only when the person wants no reply at all, never with a message step; the scenario's own level otherwise. platform_key: type: string nullable: true description: >- A new scenario the composer recognized as one of the platform's (an objection, a meeting request, ...): edit that one instead of making a duplicate. Null otherwise. notes: type: array items: type: string description: >- What the composer could not do or still needs to know (a step kind that does not exist, a cap the ask exceeds, a link the person did not give), one short line each. required: - title - trigger - goal - steps - instructions - level - platform_key - notes basis: type: object nullable: true properties: sid_or_key: type: string source: type: string enum: - platform - edited - custom key: type: string nullable: true required: - sid_or_key - source - key description: >- The scenario the draft changes, as the call named it; null for a new scenario. cost_usd: type: number nullable: true description: >- What the composition cost on the model, a few thousandths of a dollar. required: - draft - basis - cost_usd meta: type: object properties: trace_id: type: string description: UUID v7; same 128-bit value as the X-Trace-Id header. span_id: type: string pattern: ^[0-9a-f]{16}$ description: 16 hex chars, root span of this request. timestamp: type: string description: ISO 8601 UTC (Y-m-dTH:i:sZ), response time. duration_ms: type: integer minimum: 0 description: Server-side wall clock. team_sid: type: string nullable: true description: >- The team this call ran in (the token team, or the team_sid override). Null when unauthenticated; absent from pre-2026-08-20 backends. actor_type: type: string nullable: true description: >- user | agent | api_key | system. Null when unauthenticated; absent from pre-2026-08-20 backends. required: - trace_id - span_id - timestamp - duration_ms required: - success - operation - action - item - result - meta McpError: type: object properties: success: type: boolean enum: - false error: type: object properties: code: type: string enum: - validation_failed - nothing_to_update - not_found - relation_not_found - invalid_transition - limit_exceeded - payment_required - duplicate_rejected - conflict - delete_blocked - unauthorized - forbidden - rate_limited - internal_error - service_unavailable - not_implemented message: type: string recoverable: type: boolean suggestion: type: string field_errors: type: object additionalProperties: type: array items: type: object properties: rule: type: string message: type: string required: - rule - message blockers: type: array items: type: object properties: type: type: string description: >- Machine-readable blocker type (active_flow, pending_tasks, …). severity: type: string enum: - hard - soft description: >- hard = external action required; soft = acknowledge is enough. description: type: string entity_sid: type: string nullable: true count: type: integer resolution: type: string description: 'Hard: tool name to call. Soft: code for acknowledge[].' resolution_hint: type: string required: - type - severity - description - entity_sid - resolution - resolution_hint context: type: object additionalProperties: {} required: - code - message - recoverable meta: type: object properties: trace_id: type: string description: UUID v7; same 128-bit value as the X-Trace-Id header. span_id: type: string pattern: ^[0-9a-f]{16}$ description: 16 hex chars, root span of this request. timestamp: type: string description: ISO 8601 UTC (Y-m-dTH:i:sZ), response time. duration_ms: type: integer minimum: 0 description: Server-side wall clock. team_sid: type: string nullable: true description: >- The team this call ran in (the token team, or the team_sid override). Null when unauthenticated; absent from pre-2026-08-20 backends. actor_type: type: string nullable: true description: >- user | agent | api_key | system. Null when unauthenticated; absent from pre-2026-08-20 backends. required: - trace_id - span_id - timestamp - duration_ms required: - success - error responses: McpClientError: description: >- MCP error envelope. `error.code` is one of validation_failed, nothing_to_update, not_found, relation_not_found, invalid_transition, limit_exceeded, payment_required, duplicate_rejected, conflict, delete_blocked, unauthorized, forbidden, rate_limited, not_implemented. content: application/json: schema: $ref: '#/components/schemas/McpError' McpServerError: description: >- MCP error envelope with `error.code` internal_error or service_unavailable. content: application/json: schema: $ref: '#/components/schemas/McpError' securitySchemes: BearerJwt: type: http scheme: bearer bearerFormat: JWT description: >- Access token issued by gs.service.id. Its `access_identity` claim carries `team_sid`, `actor_sid` and `actor_type`, and that team scope is authoritative. TeamSid: type: apiKey in: header name: Team-SID description: >- Team scope for tokens that do not carry one. Ignored when the token already names a team. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.