> ## Documentation Index > Fetch the complete documentation index at: https://docs.rumik.ai/llms.txt > Use this file to discover all available pages before exploring further. # list tools > the account's tools (`items`), the built-in ones (`defaults`, e.g. `end_call`) and the context params every tool can template on (`contextParams`: `{phone_number}`, `{user_id}`, `{agent_id}`, `{call_id}`). ## OpenAPI ````yaml /openapi.json get /v1/tools openapi: 3.1.0 info: title: silk api version: 1.0.0 description: >- rumik ai's speech api. synthesize speech with the expressive `muga` model, the faster `mulberry` model or the multilingual `mulberry-1.6` model over http or a streaming websocket session, run conversational voice agents over webrtc, a realtime pcm socket or the phone, and manage everything the agents playground does — agents, voices, variables, tools, phone numbers, sip trunks and outbound calls — with the same api key. contact: name: rumik ai url: https://rumik.ai servers: - url: https://silk-api.rumik.ai description: production security: - bearerAuth: [] tags: - name: speech description: text-to-speech over HTTP and WebSocket. - name: voice agents description: start calls with a deployed agent from your own app. - name: agents description: build, configure, deploy and inspect your agents. - name: calls description: place outbound phone calls and read call history. - name: voices description: the voices, languages and styles an agent may use. - name: variables description: account-wide `{name}` prompt variables and their defaults. - name: tools description: HTTP tools agents call before or during a call. - name: phone numbers description: 'numbers rented through rumik: search, rent, connect, release.' - name: sip trunks description: bring your own numbers over SIP. paths: /v1/tools: get: tags: - tools summary: list tools description: >- the account's tools (`items`), the built-in ones (`defaults`, e.g. `end_call`) and the context params every tool can template on (`contextParams`: `{phone_number}`, `{user_id}`, `{agent_id}`, `{call_id}`). operationId: listTools responses: '200': description: ok. content: application/json: schema: $ref: '#/components/schemas/ToolList' examples: default: value: items: - id: 019f8e32-4d60-7f71-ac8d-9e0f1a2b3c4d name: lookup_account description: looks the caller's account up by phone number kind: before_call config: action: get performedAction: end_call curl: '' method: GET url: https://api.example.com/v1/accounts headers: - name: Accept value: application/json params: - name: phone value: '{phone_number}' body: '' timeoutMs: 3000 waitForResponse: true auth: type: bearer headerName: X-API-Key username: '' hasSecret: true llmParams: [] outputs: - name: firstName path: '' - name: plan path: account.plan isDefault: false createdAt: '2026-09-11T10:00:00Z' updatedAt: '2026-09-11T10:00:00Z' defaults: - id: default-end_call name: end_call description: ends the call kind: during_call config: action: perform performedAction: end_call curl: '' method: GET url: '' headers: [] params: [] body: '' timeoutMs: 3000 waitForResponse: true auth: type: bearer headerName: X-API-Key username: '' hasSecret: true llmParams: [] outputs: [] isDefault: true createdAt: null updatedAt: null contextParams: - id: phone_number label: phone number hint: the number on the other end of the call - id: user_id label: user id hint: your rumik account id - id: agent_id label: agent id hint: the id of the agent on the call - id: call_id label: call id hint: >- this call's id: the callId a web call returns, the call_id of a realtime session count: 1 '401': description: >- `unauthorized` — key missing, malformed, unknown, revoked or expired. content: application/json: schema: $ref: '#/components/schemas/Error' examples: unauthorized: value: error: Invalid API key code: unauthorized '403': description: '`forbidden_scope` — the key was created without the `agent` scope.' content: application/json: schema: $ref: '#/components/schemas/Error' examples: forbidden_scope: value: error: This API key lacks the 'agent' scope code: forbidden_scope '429': description: >- `rate_limited` — the key's per-minute budget is spent. `Retry-After` says how long to wait; the body carries `limit` and `current`. content: application/json: schema: $ref: '#/components/schemas/Error' examples: rate_limited: value: error: Rate limit exceeded code: rate_limited limit: 100 current: 101 headers: Retry-After: description: seconds to wait before retrying (per-key rate limit only). schema: type: integer components: schemas: ToolList: properties: items: items: $ref: '#/components/schemas/Tool' type: array description: the account's tools. defaults: items: $ref: '#/components/schemas/Tool' type: array description: the built-in tools every agent may use (`end_call`, …). contextParams: items: $ref: '#/components/schemas/ToolContextParam' type: array description: the `{tokens}` every tool receives about the call. count: type: integer type: object required: - items - defaults - contextParams - count title: ToolList Error: type: object properties: error: type: string description: human-readable error message. code: type: string description: machine-readable error code. Tool: properties: id: type: string description: the tool's id (`default-…` for built-ins). name: type: string description: type: string kind: $ref: '#/components/schemas/AgentToolKind' config: $ref: '#/components/schemas/ToolConfig' isDefault: type: boolean default: false description: >- true for the platform's built-in tools, which cannot be edited or deleted. createdAt: anyOf: - type: string format: date-time - type: 'null' updatedAt: anyOf: - type: string format: date-time - type: 'null' type: object required: - id - name - description - kind - config title: Tool description: a tool as stored. the credential is never returned. ToolContextParam: properties: id: type: string label: type: string hint: type: string type: object required: - id - label - hint title: ToolContextParam AgentToolKind: type: string enum: - before_call - during_call title: AgentToolKind description: When in a call's life the agent reaches for the tool. ToolConfig: properties: action: $ref: '#/components/schemas/AgentToolAction' performedAction: $ref: '#/components/schemas/AgentToolPerformedAction' curl: type: string default: '' method: $ref: '#/components/schemas/AgentToolHttpMethod' url: type: string headers: items: $ref: '#/components/schemas/ToolKeyValue' type: array params: items: $ref: '#/components/schemas/ToolKeyValue' type: array body: type: string timeoutMs: type: integer waitForResponse: type: boolean auth: $ref: '#/components/schemas/ToolAuth' llmParams: items: $ref: '#/components/schemas/ToolLlmParam' type: array outputs: items: $ref: '#/components/schemas/ToolOutput' type: array type: object required: - action - performedAction - method - url - headers - params - body - timeoutMs - waitForResponse - auth - llmParams - outputs title: ToolConfig description: >- Server-constructed (``serialization_alias``), see :class:`AgentToolAuthView`. AgentToolAction: type: string enum: - get - post - perform title: AgentToolAction description: What the tool does when it runs. ``perform`` is a platform action. AgentToolPerformedAction: type: string enum: - end_call - transfer_call title: AgentToolPerformedAction description: The platform actions a ``perform`` tool can carry out. AgentToolHttpMethod: type: string enum: - GET - POST - PUT - PATCH - DELETE title: AgentToolHttpMethod ToolKeyValue: properties: name: type: string maxLength: 128 value: type: string maxLength: 2048 default: '' type: object required: - name title: ToolKeyValue ToolAuth: properties: type: $ref: '#/components/schemas/AgentToolAuthType' default: none headerName: type: string default: X-API-Key username: type: string default: '' hasSecret: type: boolean default: false description: >- whether a credential is stored. the credential itself is never returned. type: object title: ToolAuth description: >- Read side: never the secret, only whether one is stored. Server-constructed, so the camelCase wire names are ``serialization_alias`` (the constructor keeps the real field names) — as the other read models do. ToolLlmParam: properties: id: type: string maxLength: 64 default: '' name: type: string maxLength: 64 type: $ref: '#/components/schemas/AgentToolParamType' default: string description: type: string maxLength: 500 default: '' required: type: boolean default: true type: object required: - name title: ToolLlmParam ToolOutput: properties: name: type: string maxLength: 65 default: '' path: type: string maxLength: 256 default: '' type: object title: ToolOutput description: >- One value the tool exposes: ``name`` is the JSON key found anywhere in the response (written ``$name`` in the dashboard); ``path`` optionally pins it to a dotted location instead. A blank name is a row left empty. AgentToolAuthType: type: string enum: - none - bearer - api_key - basic title: AgentToolAuthType AgentToolParamType: type: string enum: - string - number - integer - boolean title: AgentToolParamType description: JSON-Schema scalar types a model-supplied argument can be declared as. securitySchemes: bearerAuth: type: http scheme: bearer description: >- your rumik api key, e.g. `rk_live_...`. create one in the rumik dashboard. ````