ssh_task_poll

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

No annotations are provided, so the description carries the full behavioral burden. "Check" and "inspect" imply a non-destructive read, which is useful, but it does not say whether polling is safe to repeat, whether the task is consumed/cleared, or whether the call blocks – gaps that matter for a no-annotation 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 front-loaded sentence with no filler; the resource comes first and the operation list follows efficiently.

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 no output schema, the description does enumerate what is returned (status, exit code, log tail), which is the key missing piece. It does not cover whether the task persists or is cleared after polling, a minor gap given the otherwise complete coverage.

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%, including the nested target object, taskId, and tailLines, so the schema already documents all three parameters. The description adds no format or default detail beyond what the schema provides, so 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 set (check status, exit code, inspect log tail) against a specific resource (a background task launched via ssh_exec_background). An agent can distinguish this from ssh_exec, ssh_exec_background, and ssh_task_kill without opening any schema.

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?

Clearly ties itself to tasks launched via ssh_exec_background, which gives strong usage context. However, it never states when NOT to use it or names the alternative for stopping a task (ssh_task_kill), so routing guidance is context-rich but not complete.

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