Llm Redteam

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

The description discloses that the tool is aggressive and requires human approval, and it explicitly warns that a probe failing is a behavior, not yet an impact. It does not enumerate every side effect, but the annotations already indicate it is not read-only and not destructive, so there is no contradiction.

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 avoids unnecessary prose. The line breaks create a slightly fragmented feel, but the essential warnings and instructions are included without bloat.

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 description conveys the tool's purpose, approval requirement, and result interpretation, but it lacks parameter-level detail and does not explain the output schema despite being present. It is sufficient for a high-level understanding but not fully complete for confident 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 has 0% description coverage, and the description only partially explains the family parameter by listing valid values. The required target parameter and the model_type and generations parameters are not described, leaving the agent guessing at their meaning and format.

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 action: probe the target's AI feature with garak, one probe family at a time. It also distinguishes this from the sibling catalog tool by telling the agent to run llm_probe_catalog first to choose a family.

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 provides important usage guidance: requires human approval, should be preceded by llm_probe_catalog, and one family should be selected at a time. It also clarifies that results are candidates rather than confirmed impacts, which helps the agent interpret findings appropriately.

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