nice

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

Description adds behavioral context beyond the destructiveHint annotation: it explains subprocess execution, bounded output capture, safety timeout, and dry run capability. It also notes privilege requirements for negative adjustments. Almost fully transparent.

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?

Concise and well-structured: starts with core purpose, then details behavior and options, followed by clear exclusions. Every sentence adds value without redundancy.

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 tool with 5 parameters and no output schema, the description covers behavior, usage, and limitations well. It lacks explicit mention of return values or error handling, but these are somewhat implied by the subprocess description and timeout feature.

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 100%, so baseline is 3. The description adds semantic value by explaining how adjustment affects priority (positive lowers, negative may need privileges) and clarifying dry_run as a preview mechanism, enhancing understanding beyond schema descriptions.

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 clearly states it runs a command with adjusted niceness, specifying the verb and resource. It effectively distinguishes from sibling tools by explicitly stating what it is not for (I/O buffering, hangup immunity, time-bound execution).

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?

Provides explicit when-to-use guidance (reduce CPU impact of background tasks) and when-not-to-use with named alternatives (stdbuf, nohup, timeout). Also mentions dry_run for preview, offering a testing option.

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