scan_host

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

With no annotations, the description bears the full burden of behavioral disclosure. It discloses parallelism, waiting for all tools, and returning consolidated results with findings and next steps. However, it does not mention whether background jobs are created, resource usage/limits, or whether results are persisted, which are notable gaps for a scan orchestration tool.

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 four sentences, front-loaded with the primary action, and every sentence contributes useful information: parallel behavior, performance benefit, parameter meanings, and return shape. There is no redundant restatement of the tool name or obvious fluff.

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 the core usage (target and intensity), the execution model (parallel), and the return value (consolidated results with findings and next steps), which is adequate for a high-level scan tool. However, given the absence of an output schema and annotations, more detail about which tools are invoked and whether jobs are created would make it fully complete.

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?

Although the JSON schema provides only bare parameter names with no descriptions, the tool description compensates fully by defining 'target' as 'IP or hostname' and listing 'intensity' values with meanings: 'light' (quick scan), 'normal' (default), and 'deep' (thorough). This exceeds the schema's information and gives clear guidance for both parameters.

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 opens with 'Full parallel host scan — fires multiple tools simultaneously and waits for all,' which clearly specifies the verb, resource, and parallel/comprehensive nature. This distinguishes it from single-purpose siblings like nmap_port_scan or asset_search. The mention of target and consolidated results further solidifies the tool's purpose.

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 statement 'Reduces total recon time by 70% vs running tools sequentially' provides clear context for when to use this orchestration tool over executing individual recon tools one by one. It does not explicitly name alternatives or state when not to use it, but the efficiency framing is a useful usage signal.

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