Port Scanner API

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

The description discloses non-blocking behavior, keying by IP, poll-until-complete statuses ('complete'/'incomplete'/'failed'), result contents (open ports and banners), and rescan semantics. Annotations (readOnlyHint=false, openWorldHint=true) are consistent with this side-effecting, externally-reachable action.

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?

Four sentences, each providing necessary detail—scope, policy, polling, and rescan—with the core action first. No filler or repetition.

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 output schema handles return structure, while the description covers timing (1-5 min), non-blocking polling, status values, and result contents, making it fully actionable for an agent.

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 sole parameter rescan is already documented in the schema with full coverage; the description restates it without adding significant new semantics. Baseline 3 applies because schema covers the parameter adequately.

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 'Scan all 65535 TCP ports' of the user's own public IP, with explicit policy restriction against targeting others. This specific verb+resource+scope distinguishes it from sibling fast_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 description explains the polling pattern and rescan flag, and notes the policy restriction that only the requester's own IP can be scanned. However, it does not explicitly contrast with fast_scan or state when to prefer one over the other.

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

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

The description richly discloses behavioral traits beyond the annotations: it is non-blocking, keyed by IP, returns current state if a scan is already running, must be polled until a terminal status, and rescan forces a fresh scan. This adds significant context beyond the readOnlyHint=false and openWorldHint=true annotations.

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 dense paragraph but every sentence contributes essential operational detail (scope, policy, non-blocking behavior, polling, result contents, rescan). It is slightly verbose but appropriately sized for the complexity; there is no 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?

Given the tool's asynchronous nature, polling requirement, and output schema presence, the description provides complete guidance: it explains status values, result contents, and how to force a new scan. Combined with the schema and annotations, the agent has everything needed to invoke and interpret the tool.

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 schema covers 100% of the single parameter (rescan) with a description. The tool description adds further practical meaning by explaining the effect of rescan:true (force a fresh scan) and the default behavior, which goes beyond the schema's basic description.

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 scans the 32 most common TCP ports of the requester's own public IP, with a specific verb ('scan'), resource ('your own IP'), and scope ('common ports'). It also distinguishes from the sibling deep_scan by explicitly limiting to common ports and noting there is no target argument.

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 gives clear usage context: it explains the policy constraint (only scans the requester's own IP), the non-blocking/polling behavior, and when to use rescan:true. However, it does not explicitly mention the alternative deep_scan or state when to prefer one over the other, so it lacks explicit alternative guidance.

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