Starts call media streaming.
| Name | Required | Description | Default |
|---|---|---|---|
| uuid | Yes | Call ID. | |
| stream_url | Yes | WebSocket URL for call streaming | |
| stream_type | Yes | ||
| stream_channel | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| success | No | Indicates that the request was successful | |
| stream_id | No | Stream ID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility for disclosing behavior. 'Starts call media streaming' implies a state change but does not mention that it creates a stream resource, requires an existing call, or has any side effects or failure modes. This is minimal transparency for a mutation-like operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, brief sentence, which is concise and front-loaded. However, it is under-specified rather than efficiently informative; it does not contain enough content to be highly useful, but it is not verbose either.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having an output schema, the description is incomplete in context. It does not mention that streaming applies to an active call, that a WebSocket URL is required, or describe the oneway/twoway distinction. Given the tool's complexity and the absence of annotations, more context is needed for confident invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no parameter-level meaning beyond the schema. Schema coverage is only 50%, so the description should compensate but does not. It fails to explain how uuid, stream_url, stream_type, and stream_channel relate to the streaming action, leaving the agent to rely solely on the schema's descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Starts call media streaming' uses a specific verb ('Starts') and resource ('call media streaming'), clearly distinguishing it from sibling tools like call_control_streams_delete and call_control_audio_play. It accurately and succinctly states the tool's purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool, prerequisites (e.g., an active call), or how it compares to alternatives like call_control_audio_play. It is a single statement with no contextual framing, leaving the agent to infer usage from the name and schema.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools are organized by resource with a clear action suffix (create/list/get/update/delete), making most purposes distinct. However, with 122 tools, some pairs like `cdrs_list` vs `cdrs_list_all` or `ten_dlc_brand_campaigns_list` vs `ten_dlc_campaigns_list` could cause confusion without careful reading of descriptions.
All tool names follow a consistent `resource_action` snake_case pattern (e.g., `api_keys_create`, `call_control_answer`, `ten_dlc_brands_list`). Verbs are standardized across the set, with only a few exceptions like `check` or `nudge` that still fit the verb-first style. No mixed casing or inconsistent separators.
At 122 tools, this is an extremely large surface that overwhelms the typical MCP agent's ability to select the right tool. Even though the count reflects the full Wavix API, the sheer number far exceeds the 50+ threshold for 'extreme mismatch' and is impractical for most use cases.
The tool set covers a broad range of communications features: numbers, calls, messages, billing, CDRs, sub-accounts, 10DLC compliance, speech analytics, and WebRTC. Missing operations like `sub_accounts_delete` or a 2FA service management endpoint are minor gaps that can be worked around via portal or other tools, but overall lifecycle coverage is strong.
