hashcat

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

With no annotations supplied, the description carries the behavioral burden. It discloses the mandatory mode-number requirement, the output shape (cracked hashes and plaintext passwords), and the presence of status lines for speed/progress. It does not detail failure modes or GPU/OpenCL prerequisites beyond calling itself GPU-accelerated, but the key call-time behavior is clear.

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 moderately sized but each sentence earns its place: use case, requirement, alternatives, and output behavior. The only minor excess is the marketing-style 'World's fastest' opener, but it does help convey the tool's distinguishing performance niche.

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 complex tool with no output schema and no annotations, this is reasonably complete: it covers purpose, mode requirement, alternatives, output, and progress feedback. It could add how to handle uncertain hash types (though it points to hash_identifier) and what happens with a wrong mode, but nothing essential for invoking the tool is missing.

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 description coverage is 100%, so this dimension is baseline 3. The description reinforces that mode is mandatory and mentions output semantics, but it does not add meaning beyond the schema's property descriptions, which already include key mode values and examples in opts.

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 identifies a concrete action (high-performance cracking), a specific resource domain (hash sets), and an environment (GPU-accelerated, 300+ modes). It also explicitly contrasts itself with john, giving an agent a clear way to distinguish this offline GPU cracker from sibling tools.

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?

It gives a when-to-use signal ('Use for high-performance cracking of large hash sets'), a hard precondition ('REQUIRES the mode number matching the hash type'), and clear alternatives with routing conditions ('For CPU-only or auto-detect cracking, use john instead'; 'Use hash_identifier first if unsure'). This is explicit selection guidance.

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