Node Tasks

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description's 'Query' wording is consistent with that. It adds the useful distinction that list returns recent tasks and get requires a UPID, but it does not disclose pagination, result shape, or any rate-limit/auth caveats. This is acceptable but not rich.

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?

The description is one compact, scannable line that front-loads the resource and then uses a pipe-separated action mapping. There is no filler or needless repetition of schema details.

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?

For a small read-only query tool with only three parameters, the description plus schema covers the essential call decisions: which node, which action, and that get needs a UPID. The missing pieces are minor, such as pagination for list and output shape, and the read-only annotation removes the need for safety caveats. It is complete enough to invoke correctly, though explicit sibling routing would make it a 5.

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?

The schema documents node and upid but leaves the action enum values semantically undeclared; the description fills that gap by mapping list -> recent tasks and get -> task details by UPID. It also implies upid is relevant for get, which is useful beyond the raw schema. It does not describe the UPID format, but that is a minor omission.

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 uses a specific verb ('Query') and resource ('node tasks'), then breaks out the two action modes: list recent tasks and get task details by UPID. It is clear what the tool operates on, but it does not explicitly distinguish itself from sibling tools like proxmox_node_log, so it stops short of a 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?

There is no guidance about when to prefer this tool over siblings such as proxmox_node_log, nor any exclusions or context like 'use for task history instead of logs'. The only usage direction is the action mapping, which helps select list vs get but does not help choose between this tool and alternatives.

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