mimikatz

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 mentions the tool extracts credentials but omits critical behavioral traits: it requires elevated privileges (e.g., admin/seebug), may trigger antivirus or endpoint detection, and could crash the LSASS process if used carelessly. For a well-known post-exploitation tool, this is a significant gap. The example in the schema hints at privilege escalation, but the description itself does not disclose these risks.

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 compact and front-loaded: two sentences that immediately convey the tool's role, target platform, and output. There is no fluff or repetition, and every sentence 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?

The tool is complex with many subcommands, but the schema only exposes one free-form string. The description covers the output format at a high level but omits prerequisites (admin rights, Windows environment), potential side effects, and error handling. An agent might not know that 'privilege::debug' is required or that the tool can be detected. Given the absence of annotations and output schema, more operational detail is needed to ensure correct and safe invocation.

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 already provides 100% coverage for the single parameter 'opts', including a concrete example command. The description adds no further meaning beyond confirming the tool's purpose. Since schema coverage is high, a baseline of 3 is appropriate; the description does not need to re-document the parameter, but it also doesn't enrich it.

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's specific purpose: extracting plaintext passwords, NTLM hashes, Kerberos tickets, and PINs from memory (LSASS) on a compromised Windows system. It uses a specific verb (extracting/dumping) and a precise resource, making it easy to distinguish from sibling tools that perform scanning, network, or cracking tasks.

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 explicit context on when to use it: 'Use on a compromised Windows system to dump credentials.' While it doesn't list alternatives or exclusions, the context is clear enough for an agent to select it over network-scanning or password-cracking tools. It could be improved by noting that it's specifically for post-exploitation credential access rather than initial reconnaissance.

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