recon_sweep

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

No annotations are provided, so the description carries the full burden. It discloses passive-only nature, the specific tools used (subfinder, amass -passive, theHarvester), that it records under a scan run, change detection behavior, tracking of disappeared assets, and the priority_new_assets output. It also notes required scope for the domain. While it omits details like async behavior or run cancellation, the key behavioral traits are well covered.

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 well-structured: a one-sentence summary, a functional paragraph, a safety/rationale sentence, and a parameter list. Each sentence adds value and the key points are front-loaded. It is slightly longer than absolutely necessary, but there is no wasted content.

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?

No output schema exists, so the description must explain return values, and it does by listing the categories of changes (new subdomains, IPs/ports, endpoints, vulnerabilities, disappeared assets, priority_new_assets). Combined with parameter details and usage context, it gives a near-complete picture. Minor omissions include exact output format and status details, but these are not critical for tool selection.

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 input schema has 0% description coverage, but the description provides detailed semantics for all 4 parameters: domain (must be in active program scope), program (defaults to domain), tools (subset with default all), and tool_budget (max count, 0=no limit). This fully compensates for the schema's lack of descriptions and adds meaning beyond the type system.

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 a specific action and resource: 'Passive recon sweep with change detection.' It enumerates concrete outputs (new subdomains, new IPs/ports, new endpoints, new vulnerabilities, disappeared assets) and distinguishes itself from sibling tools like subfinder_enumerate and asset_diff_runs by combining enumeration with change detection across runs.

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 implies when to use the tool: repeatedly/unattended for passive recon and change monitoring, stating 'Safe to run repeatedly/unattended (passive only).' It explains the rationale for priority_new_assets and mentions the scope constraint. However, it does not explicitly exclude alternatives or contrast with individual enumeration tools, so it is clear but not fully explicit.

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