MacroCyber

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

Annotations already mark it readOnly, openWorld, idempotent, and non-destructive. The description adds substantial behavioral detail: it reads only what a logged-out visitor can see, NEVER asserts an exploit, distinguishes confirmed observations from heuristic checks, notes a 15–25 second runtime, and mentions per-caller/per-host rate limits. This significantly enriches the behavioral profile without contradicting the annotations.

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 somewhat long but every sentence carries essential information: purpose, output components, safety guarantees, use case, and performance characteristics. It is front-loaded with the primary action and outcome, followed by the behavioral constraints and usage guidance. It is efficient despite its length, earning a 4 rather than 3.

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?

Given the tool's complexity (multiple output types like SSVC decision, score, enablers, chains) and lack of an output schema, the description fully compensates by listing all return components explicitly. It also covers timing, rate limits, safety, and intended use case. With only one parameter, nothing an agent needs to call it correctly 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?

With only one parameter (url) and 100% schema coverage, the schema already document the parameter fully. The description adds no new parameter-specific semantics beyond implying the URL should be a public website, which is a marginal addition. Per rubric, high schema coverage sets a baseline of 3, and the description does not meaningfully exceed 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 verb (Run an assessment), the resource (public website), and the specific output (signed, exploitability-graded exposure claim). It distinguishes itself as passive and external, which clearly separates it from potentially more active or intrusive tools. The purpose is unambiguous and action-oriented.

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 gives a concrete use case: 'check what a public website or web app exposes to the internet, for example right after deploying an AI-built app.' This provides clear context for when to use the tool. However, it does not explicitly mention when not to use it or list alternatives, which keeps it below a 5.

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