Fetch and summarize a run's SSE stream, capturing status, assistant, thinking, tool_call, and result events plus tail text to monitor agent execution.
Fetch SSE run stream and summarize: status/assistant/thinking/tool_call/result events, tail text.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Agent id | |
| runId | Yes | Run id | |
| maxChars | No | Max assistant text chars (default 8000) |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It hints that the output is a summary of event types rather than raw SSE bytes, which is useful, but it omits key traits: whether the call blocks until the run finishes, whether it works on in-flight runs, auth requirements, or truncation behavior. Significant gaps for a streaming tool.
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?
A single tight sentence, front-loaded with the core action and the event summary that follows. No filler, though it is terse to the point of under-specifying behavior.
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?
Three parameters and no output schema, so the description's enumeration of summarized event types partially compensates. However, for a streaming tool with zero annotations and no output schema, it should clarify blocking/liveness behavior and result shape more than it does.
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 100%, so all three parameters (id, runId, maxChars with default 8000) are already documented. The description's mention of 'tail text' loosely relates to maxChars' truncation role but adds no syntax or format detail beyond the schema. Baseline 3 applies.
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?
States a specific verb+resource ('Fetch SSE run stream') and adds what the result contains (status/assistant/thinking/tool_call/result events, tail text). This distinguishes it from get_run/list_runs reasonably well, though the description never explicitly names a sibling.
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 indication of when to choose this over get_run, list_runs, or get_conversation. The agent must infer that this is the streaming/summary view rather than a metadata fetch, and there is no guidance on prerequisites (e.g. whether the run must be complete first).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.