run_attack

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

No annotations provided, so description carries full burden. It states starting a new conversation and optional scoring, but does not disclose side effects, authorization needs, or rate limits. Basic behavior is disclosed, but not exhaustive.

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?

Two short sentences with clear structure. No redundant words. Could be slightly more concise but no fluff.

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?

With 6 parameters, 3 required, and no annotations, description should provide enough context. It misses explanations for critical parameters like objective and engagement_id. Output schema exists, so return values need not be explained, but input semantics are incomplete.

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 0%, so description must add meaning. It explains attack_name and scorer_names, but fails to describe objective, engagement_id, attack_params, or memory_labels. Only partial guidance for 2 out of 6 parameters.

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?

Description clearly states the tool runs a named PyRIT attack strategy against the engagement's configured target. It distinguishes itself from sibling continue_attack by noting that this starts a new conversation. The verb 'run' and resource 'attack strategy' are specific.

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?

Explicitly says to use when starting a new conversation, and points to continue_attack for continuing within the same conversation. Does not mention exclusions or when not to use, but the context is clear enough.

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