task_log

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

No annotations are provided, so the description carries the full burden. It explicitly marks the tool as 'READ', describes the return structure, warns about truncation, and explains the node parameter behavior. This is transparent beyond the schema.

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 multi-line but efficiently structured: a one-line summary, a code block for return format, and an Args list. It is front-loaded with the key purpose and return format, but could be slightly shorter without the code block example.

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?

The tool has 4 parameters and no output schema. The description covers the return format, the truncation handling, and parameter details. It is complete for an agent to understand how to use the tool correctly.

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?

With 0% schema description coverage, the description compensates fully. The Args section explains each parameter: upid (required), limit (default 200), target (Proxmox target), and node (omit to parse from UPID). This adds significant meaning beyond the schema's type/default information.

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 begins with '[READ] Fetch the log lines of an async task by its UPID.' This clearly states the action (fetch) and resource (log lines), distinguishing it from sibling tools that focus on VMs, nodes, etc.

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?

The description explains the return format and notes the 'truncated' field, advising to raise limit or narrow the query if truncated is true. It does not explicitly state when not to use this tool, but the context is clear given the variety of siblings.

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