audit_domain

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

Annotations already indicate read-only, idempotent, nondestructive, but the description adds critical context: credit cost (6), rate limits (30/hr free, 500/hr Pro), TXT record filtering behavior, and that next_calls are emitted. No contradictions.

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 a single cohesive paragraph covering multiple aspects efficiently. Some minor redundancy in explaining filtering, but overall well-structured and front-loaded with the core purpose.

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 complexity (3 sub-tools, rate limits, filtering, chaining), the description covers all necessary context. It names the return fields (domain, report, etc.) so agents know what to expect. No gaps.

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?

Both parameters have schema descriptions. The description adds significant meaning: explains filtering for include_all_txt, its default, why filters exist (vendor verification strings), and that total_txt_records always shows pre-filter count.

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 performs a comprehensive domain audit combining domain_report, live HTTP security headers, and technology fingerprinting. It explicitly distinguishes itself from the sibling tool domain_report by contrasting passive-only vs. active checks.

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?

Explicit guidance is provided: 'Use when you need the full picture (recon + active checks); use domain_report for passive-only assessment.' It also explains how to chain with subdomain_enum and ssl_check for residual recon depth.

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