Llm Scan Config

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

The description discloses important behavioral traits not present in annotations: '[AGGRESSIVE — requires human approval]' signals a high-impact action needing consent. This goes beyond the minimal readOnly/destructive flags and informs the agent of the approval requirement.

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 and front-loaded, starting with the critical approval warning followed by the core action and usage rationale. Every sentence adds value without redundancy, making it efficient for an agent to parse.

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 gives enough context for an agent to understand when and why to use the tool, and the output schema exists so return values need not be detailed. However, the lack of parameter descriptions and precise engine/enum values leaves minor gaps in the overall call context.

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 provides zero descriptions for target, config_path, or engine. The description only implies that config_path refers to 'a config inside the workspace' and mentions engine values 'promptfoo or deepteam' implicitly, but target remains completely unexplained, leaving the agent to guess its 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 tool's function: 'Run a promptfoo or deepteam suite from a config inside the workspace.' It also distinguishes itself from generic alternatives by emphasizing target-specific, application-aware probes, which sets it apart from sibling tools like llm_redteam.

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 explicitly provides when-to-use guidance: 'Use this when you have a target-specific test suite' and contrasts with generic probes. This gives clear selection criteria relative to other scanning tools, though it does not name specific alternatives.

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