nand_usage

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

No annotations are provided, so the description carries the full burden. The phrase 'read-only' is a basic behavioral disclosure, but it doesn't explain what happens if NAND is inaccessible or whether it requires any special permissions (though likely not). It also doesn't mention whether it returns a snapshot or aggregates data over time. The bare-bones description doesn't contradict annotations, but it's minimally informative.

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 short phrase, which is appropriately concise for a tool with no parameters. It's front-loaded with the key information ('NAND storage usage') and the read-only constraint. It doesn't waste words, so it's well-structured for its simplicity.

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?

Given the tool's low complexity (no params, no output schema), the description is acceptable but not complete. It doesn't specify the units of usage (bytes, blocks, percentages) or whether it includes bad block information (which is likely covered by nand_bad). An agent might not know if this returns simple capacity numbers or detailed per-block usage. A bit more detail on the output format would improve completeness.

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?

This tool has zero parameters, so the description doesn't need to explain parameter details. Per the rubric, 0 params earns a baseline 4. The description adds minimal value, but since there are no parameters, there's nothing to compensate for. The description correctly implies this is a no-argument query.

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 'NAND storage usage (read-only)' clearly identifies the action (querying usage) and the resource (NAND storage), and the read-only hint is explicit. However, it lacks detail on what specific metrics are provided (e.g., total, used, free space, bad blocks), which is common for sibling tools like nand_bad. It distinguishes itself from nand_bad by focusing on usage, but more specificity would be better.

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 a read-only query operation, but there is no explicit guidance on when to use this tool vs nand_bad or other storage-related tools. Given the large sibling list, naming alternatives or scenarios would be helpful. However, the read-only hint gives some context that this is a safe query, so it's not completely lacking.

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