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

Annotations already cover read-only, idempotent, closed-world, non-destructive behavior. The description adds genuinely new context: no account or API key is required, no target requests or scans are executed, and the returned instructions are test data rather than instructions to follow — a critical framing for injection content. It stops short of describing the returned text's structure or volume, but with a text payload that gap is minor.

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?

Three sentences, zero waste, leading with what is retrieved before the authorization caveat and the sibling routing. Every clause earns its place.

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 single-enum-parameter read tool with no output schema, the description covers purpose, safety framing, auth preconditions, execution scope, and alternative tools. Nothing an agent needs in order to select or invoke it 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% with a fully enumerated category parameter, so the schema already carries the semantics. The description only restates 'one attack category' without adding format or selection guidance beyond the enum, which is the expected baseline when the schema does the lifting.

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?

States a specific verb and resource (retrieve bundled prompt-injection test inputs as text) scoped to one attack category, and explicitly differentiates itself from siblings map_owasp_llm_risk and build_test_pack. An agent can distinguish all three without opening a schema.

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?

Names the alternatives and the condition that selects each: map_owasp_llm_risk for risk-based guidance, build_test_pack for packaging response checks. It also states the authorization precondition (a chatbot/API the user owns or is authorized to test), removing any ambiguity about when this is appropriate.

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