disk_temperatures

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 discloses that it reads from `smartctl -A`, implying a read-only operation, but does not mention permissions, failure modes, or the exact output format. For a simple read-only tool this is adequate, but it lacks detail on return structure or behavior when no disks are present.

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 a single, clear sentence that states the purpose and method without unnecessary words. It is front-loaded and every word adds value.

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 zero-parameter tool with no output schema, the description is sufficient: it names the metric (°C), the scope (every physical disk), and the method (`smartctl -A`). It does not specify the return layout, but given the simplicity and sibling context (e.g., `list_disks`), an agent can infer a list of disk-to-temperature mappings. This is slightly below perfect only because it omits mention of what happens if SMART data is unavailable.

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 tool has zero parameters, so the baseline is 4. The description correctly notes no parameters via the empty schema, and there is nothing more to explain. The method mention adds context but no parameter-specific information is needed.

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 states a specific verb ('reports') and resource ('temperature of every physical disk'), with the method (`smartctl -A` per disk). It clearly distinguishes itself from sibling tools like `cpu_temp` (CPU temperature) and `smart_attributes` (detailed SMART attributes), which could also include temperature but with a broader scope.

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 usage: use when disk temperatures are needed, especially per-disk values. It doesn't explicitly mention alternatives, but given the zero-parameter design and clear purpose, an agent can easily infer when to call this tool. No exclusions or edge cases are noted, but simplicity makes this acceptable.

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