shred

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

Beyond the destructiveHint annotation, the description details irreversibility ('shredded data is unrecoverable') and the need for explicit confirmation via --allow_destructive, adding valuable behavioral context not present in annotations alone.

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 concise with 4 sentences, front-loading the main action. However, it could be slightly more streamlined; the inclusion of 'See also rm' is helpful but not strictly necessary.

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 simplicity and full parameter coverage in the schema, the description provides complete context: purpose, when to use, behavioral traits, and parameter hints. No output schema exists, but the tool's output is minimal and non-essential.

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?

With 100% schema coverage, the description adds value by explaining the purpose of key parameters: --allow_destructive as confirmation and --dry_run for preview. This enhances understanding beyond the raw 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 the tool overwrites file contents with random data and optionally removes files. It distinguishes itself from the sibling 'rm' by specifying it is for secure erasure of sensitive files, not simple deletion.

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: 'to securely erase sensitive files beyond forensic recovery' and when-not-to: 'Not for simple deletion — use rm for non-sensitive files.' It also mentions using --dry_run for preview and requiring --allow_destructive confirmation, giving clear operational guidance.

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