host_discovery

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

No annotations are provided, so the description carries the burden. It discloses the method (nmap -sn, a ping sweep), the return type (structured dict with status, raw output, command, and mode), and prerequisites (target authorized and in scope). It does not elaborate on network side effects or permission requirements beyond scope, but for a read-only ping sweep, the disclosure is adequate and adds meaningful detail beyond the tool's name.

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 opens with a concise one-line summary, then provides structured fields (TOOL_NAME, USECASE, INSTRUCTIONS, etc.) for easy parsing. Some redundancy exists (e.g., TOOL_NAME repeats the tool name, DISPLAY_NAME is redundant), and the block contains repeated scope reminders, but the overall structure is organized and front-loaded. It is verbose but not wasteful enough to earn a 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?

For a one-parameter tool with an output schema, the description covers all necessary context: input description, output description, an example (host_discovery("10.0.0.0/24")), prerequisites, and related tools. It also outlines the structured result fields. This is complete for the tool's complexity.

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 zero description coverage, but the description fully compensates: 'target: Host, IP or CIDR to sweep (must be in scope).' It clarifies the type (host/IP/CIDR) and the constraint (in-scope). This is exactly what an agent needs to correctly populate the parameter.

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's function: 'Ping-sweep a host or range to find live hosts (nmap -sn).' It uses a specific verb ('sweep') and resource ('host or range'), and mentions the scope of the operation ('without port scanning'), effectively differentiating it from sibling tools like nmap_scan and masscan_scan.

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 USECASE field provides clear context: 'Enumerate which hosts in an in-scope range are up, without port scanning,' implying when to use it. RELATED_TOOLS lists nmap_scan and masscan_scan, but without explicit comparative guidance. There is no direct 'when not to use' statement, but the 'without port scanning' phrase suggests a boundary. This is strong 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.