Read new output events from a persistent process session to monitor commands and retrieve incremental results. Omit the cursor for new output or provide one to replay from a specific position.
Read new output events from a persistent process session. Omit cursor for incremental reads; provide cursor for explicit replay position.
| Name | Required | Description | Default |
|---|---|---|---|
| cursor | No | ||
| waitMs | No | ||
| sessionId | Yes |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, non-destructive, openWorld=false, but idempotentHint=false is notable and the description explains why: omitting the cursor consumes new events incrementally while supplying one replays from a fixed position. That stateful-consume behavior is genuine value beyond the annotations, though waitMs semantics and buffer/consumption behavior remain undisclosed.
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?
Two tight sentences with the core action first and the cursor semantics second. No filler, nothing repeated from the schema.
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?
No output schema exists, yet the description never characterizes the returned events or the cursor value an agent should pass next, and waitMs is unexplained. For a streaming-read tool this leaves real gaps an agent would need to probe at runtime.
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%, so the description must carry the param burden. It explains cursor's two modes well, but sessionId is left to the schema and waitMs (a 0-10000 long-poll-style delay) is never explained despite being the least self-evident parameter.
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: reading output events from a persistent process session. The scope word 'persistent process session' separates it from fs_read and search, though it never names a sibling or explains the boundary with process_input.
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 gives conditional guidance for the cursor parameter (omit for incremental, provide for replay), which is really parameter usage rather than tool selection. It offers no statement of when to reach for this tool versus process_list, process_input, or fs_read.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.