inference_stream[inference] Streaming inference with chain-of-thought
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"messages": "<messages>"
},
"name": "inference_stream"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| messages | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the remaining burden is describing the streaming behavior itself — chunk format, termination, whether partial results are usable — and none of that is present. 'Streaming' and 'chain-of-thought' are keywords, not disclosure, and with no output schema the description is the only place this could have been explained.
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?
It is short and front-loaded, with no filler sentences. But the brevity here is under-specification rather than economy, so it earns only a middle score.
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?
A streaming tool with no output schema and no parameter documentation needs the description to explain the return channel and result format; it does neither. An agent knows the name of the capability but not enough to call it correctly or interpret the response.
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?
Schema description coverage is 0% for the single required 'messages' parameter; the schema only carries inline descriptions on the nested role/content fields. The description says nothing about message ordering, whether a system message is allowed, or how the array shapes the output — leaving the one parameter effectively undocumented in prose.
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 gives a verb-ish phrase ('Streaming inference') plus a distinctive modifier ('chain-of-thought'), which hints at how it differs from the sibling 'inference' tool. However, '[inference]' merely repeats the resource and the phrase is terse; it never states what the tool actually produces or how streaming differs operationally.
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?
No statement of when to choose this over the sibling 'inference' tool, no prerequisites, and no exclusions. The word 'Streaming' implies a use case but the agent must infer it.
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.