email_harvest

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'passive' and 'free/no-key sources', which hints at non-intrusive behavior, but does not explicitly state that the tool is read-only or what side effects (if any) it might have. It also does not mention rate limits or permission requirements beyond scope authorization, leaving some transparency gaps.

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 with a concise first line followed by key-value metadata and an Args section. There is some redundancy between INPUT_DESCRIPTION and Args, and the USECASE largely repeats the first line, but overall it is efficient and front-loaded. Slightly longer than necessary due to redundancy, but still a solid 4.

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?

The description covers all essential aspects: purpose, use case, instructions, prerequisites, input parameters, output structure (Structured result dict including parsed emails), examples, and related tools. Given the tool's moderate complexity (3 parameters, 1 required), this is comprehensive and provides enough context for an AI agent to know when and how to invoke it.

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's Args section fully compensates by explaining each parameter: domain (apex domain, must be in scope), sources (comma-separated theHarvester sources, default free/no-key), and limit (max results). This exceeds what the schema provides and gives essential guidance for using the tool correctly.

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 first line clearly states the verb (harvest), resource (emails, subdomains, hosts), and method (theHarvester, passive), making the purpose immediately obvious. The USECASE adds more detail about collecting from search engines and CT logs, which also distinguishes it from sibling tools like dns_recon or subdomain_enum by emphasizing email discovery.

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 provides clear usage context: 'Collect public emails, subdomains and hosts for an in-scope domain', along with instructions and prerequisites (domain must be in scope). It also mentions related tools (subdomain_enum, dns_recon) but does not explicitly say when NOT to use this tool versus those alternatives, so it falls short of a perfect 5.

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