smart_attributes

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

With no annotations, the description carries the full burden and does disclose the underlying command (`smartctl -A`) and that it returns an attribute table plus temperature and power-on hours, which is good. However, it does not cover potential failure modes (e.g., device not supporting SMART), permission requirements, or the exact output format, 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 two sentences long, with the primary action front-loaded and the parameter clarification placed in the second sentence. Every word earns its place; there is no fluff or 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 simple tool with a single parameter and no output schema, the description is adequately complete: it states what data is returned (full table plus temperature and power-on hours) and how to specify the device. It could be more thorough about error handling or return structure, but given the minimal scope, it covers the key contextual needs without being overly verbose.

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 provides zero description for the 'device' parameter, so the description compensates by explicitly stating that `device` is 'sda' or '/dev/sda'. This adds concrete format examples, which is essential for correct invocation and goes beyond the lone schema property name. A minor gap is that it doesn't clarify whether partitions or other device identifiers are acceptable, but it's sufficient for typical usage.

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 tool retrieves a full SMART attribute table for a single device using `smartctl -A`, plus temperature and power-on hours. This is specific (verb 'Full SMART attribute table' + resource 'one device') and distinguishes it from siblings like smart_status (which likely covers only health status) and disk_temperatures (which likely covers only temperature data).

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 implies when to use this tool (when full SMART attribute details are needed) by specifying its output, but it does not explicitly mention alternatives or when not to use it. There is no 'use X instead' guidance, so it remains at the implied-usage level.

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