disks/performance

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

With no annotations, the description carries the burden of behavioral disclosure. It states the output content (read/write sectors, merged operations, wait times in ms) and the equivalence to iostat, implying read-only behavior. However, it does not disclose potential requirements (e.g., root privileges), error behavior for invalid devices, or whether it samples instantaneously or over a period, leaving some behavioral gaps.

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 three sentences with zero fluff. The first sentence front-loads the core purpose, the second details output, and the third gives usage guidance and an alternative. Every sentence earns its place.

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 only two optional parameters and no output schema, the description is fairly complete. It describes the returned metrics, the prerequisite for a valid device, and a sibling alternative. It omits edge cases like default behavior when device is omitted or error handling, but given the simplicity and the mention of iostat equivalence, it is adequate for an agent to invoke 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?

Schema coverage is 100% with both parameters documented. The description adds value beyond the schema by linking the 'device' parameter to the prerequisite of using disks/list, and by clarifying the nature of the metrics returned. This enriches the meaning of the output_format parameter by giving context on what the output contains, exceeding the baseline.

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 the verb 'Retrieves' and the resource 'granular block device I/O performance metrics', explicitly equating it to iostat. It distinguishes itself from siblings by contrasting with disks/free for static capacity, making its purpose unmistakable.

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 provides a clear prerequisite ('Use disks/list first to find valid block devices') and identifies a specific alternative ('If you want static capacity instead, use disks/free'). It does not cover all sibling distinctions (e.g., health, usage) but gives practical routing guidance for the most common confusion.

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