Read persistent process output

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so safety is covered. The description adds real value by disclosing cursor-based incremental semantics and that the call may block briefly for new output — behavior not visible in annotations. It does not disclose what happens on an invalid or stale cursor, whether output is truncated by maxBytes, or how waiting interacts with defaults.

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 tightly written sentences with no filler, and the core read semantics and cursor mechanism are front-loaded. Slightly under-informative rather than verbose, which is the right failure direction but leaves gaps.

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?

Six parameters, 0% schema coverage, and no output schema, yet the description says nothing about the return shape — the agent cannot tell whether the new cursor is echoed back, how stdout and stderr are separated, or how truncation is signalled. For a cursor-based streaming read where the returned cursor is essential to the next call, that is a meaningful omission.

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% with 6 parameters, so the description must carry weight; it explains the cursor parameter's role and implicitly the wait behavior (waitMs). It says nothing about sessionId being required, maxBytes truncation, or deviceId/deviceName, leaving half the surface to name inference.

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 ('Read new stdout/stderr events from a process session') plus the incremental mechanism ('using a cursor'), so the agent knows this is a delta-read rather than a full dump. It does not differentiate itself from the very similarly named sibling read_process_output, leaving some ambiguity about which reader to pick.

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?

'Can wait briefly for new output' implies long-poll / tail-style usage, which is useful implied guidance. But there is no explicit statement of when to choose this over read_process_output, process_write, or a plain shell run, and no exclusion guidance for the closely-related sibling.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.