task_status

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

Annotation already declares readOnlyHint=true, and the description is consistent with that. It adds the non-obvious default that the node is parsed from the UPID when omitted, but says nothing about what polling returns (running/stopped/exit status), whether it blocks or errors on an unknown UPID.

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?

Front-loaded with a [READ] marker and a one-line purpose before usage and args. Slight redundancy: the node-from-UPID rule appears both in the prose and in the Args list.

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?

There is no output schema, so the description is the only place an agent could learn what a poll yields (completion state, exit status, log reference). The guidance on calling the tool is complete, but the return-value picture is not.

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 coverage is 0%, so the description must carry the load, and its Args block documents all three parameters beyond the bare types: upid's provenance, target as a config name, and node's optionality plus derivation rule.

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?

Specific verb (poll) plus resource (Proxmox async task) and concrete task examples (clone/migrate/backup), scoped by the UPID identifier. It does not explicitly distinguish itself from the sibling task_log, which likely also takes a UPID, so it falls short of full sibling differentiation.

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?

States clearly when to use it: after a write that returned a task UPID, to check completion, and explicitly warns against re-issuing the operation. No alternative tool (e.g. task_log) is named, so the routing is clear but not exhaustive.

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