read_process_output

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

No annotations are provided, so the description bears the full burden. It usefully discloses that the read is paged ('bounded page') and that the return includes both output and status, which an agent could not infer from the schema alone. However, it omits important traits: whether reading consumes or drains buffered output, whether the call is safe/non-destructive, how output behaves after the process exits, and any size or rate limits beyond the parameter bounds.

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?

One sentence, front-loaded with the verb and resource, with no filler. Its brevity edges toward under-specification rather than waste, but structurally it is well-formed.

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 three parameters, no output schema, and no annotations, the description should do more explaining than it does. It adequately conveys the return contents ('output and status') and the paged nature of the call, but it leaves open whether output persists after process exit and how status should be interpreted.

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 compensate for three undocumented parameters. But it only hints at limit/offset via 'a bounded page' and at sessionId via 'agent process session'; it never explains whether offset is an absolute cursor or advances a read pointer, whether limit is bytes or lines, or what the defaults mean. The schema carries the type and default information, so this is not a total void, but it is thin.

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 names a specific verb and resource: 'Read a bounded page of output and status for an agent process session.' This clearly places it as the read counterpart to start_process and list_processes. It stops short of explicitly naming siblings, 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?

It says nothing about when to call this rather than list_processes, run_command, or start_process, and gives no prerequisite context such as requiring a sessionId from start_process or how to discover a valid session. The intended use is inferable from the phrase 'agent process session' but never stated.

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