Wait for task events, a terminal state, or required user input. Timeouts return without stopping the task; use the next cursor to continue monitoring.
Wait for task events, terminal state or required user input. Timeout returns without stopping the task. Continue with next_cursor.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| task_id | Yes | ||
| after_cursor | No | 0 | |
| include_partial | No | ||
| timeout_seconds | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare a safe read (readOnlyHint=true, destructiveHint=false, openWorldHint=false), but the description adds the non-obvious blocking behavior: a timeout expires without terminating the task, and results are continued via a cursor. That is exactly the kind of trait an agent cannot infer from the annotations. It omits the 60-second maximum wait and whether partial data can come back.
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?
Three short sentences, front-loaded with the core purpose and followed by the two behavioral facts that matter. Nothing is padded, though the terseness is partly why the parameter and return semantics go unexplained.
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?
With five undocumented parameters, no output schema, and a polling/long-wait contract, the description is too thin. An agent learns how to continue a stream but not what a call returns, what happens to partial events, or how limit interacts with paging. The cursor/paging loop is the only area adequately covered.
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% across five parameters, so the description must carry the load, and it does not. It mentions 'next_cursor', which does not match the actual parameter name 'after_cursor', and says nothing about limit, include_partial, or the 0-60 timeout_seconds bound. The one cursor reference is at least directionally useful, which keeps this above 1.
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 and resource: 'Wait for task events, terminal state or required user input.' That clearly separates it from the fire-and-forget siblings like send_message and get_message, which return immediately. It stops short of naming a sibling explicitly, so it lands at 4 rather than 5.
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?
'Timeout returns without stopping the task. Continue with next_cursor' gives a concrete loop pattern for repeated calls, which is genuinely usable guidance. However, it never says when to prefer this over get_status or get_message, nor whether calling it is required before reading results, so the when-to-use guidance is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.