start_deep_scan

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

The description states 'Read-only — no domain mutation' but annotations set readOnlyHint: false, implying the tool is not read-only. This is a direct contradiction. While the description adds useful behavior like returning scanId and polling instructions, the contradiction invalidates the behavioral transparency score.

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 and each sentence adds real value: what it does, return behavior, read-only claim, use cases, alternatives, and abort mechanism. No filler or redundancy, and it is front-loaded with the core purpose.

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 complexity (long-running, asynchronous), the description explains the immediate return of scanId, polling via get_deep_scan_status, cancellation, and no-auth requirement. It also covers domain constraints implicitly through schema. For a tool with no output schema, this is complete and self-sufficient.

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?

Schema description coverage is 100%, and the tool description adds no additional parameter semantics beyond the schema. It does not elaborate on domain, scanType, or name beyond what the schema already provides. Baseline 3 is appropriate because the schema does the heavy lifting.

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 action: 'Start a long-running Internet.nl deep scan' with resource scope. It explicitly differentiates from sibling tools by naming scan_domain and cancel_deep_scan, explaining when to prefer this tool. The purpose is specific and unambiguous.

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?

Provides explicit when-to-use guidance: 'Use when scan_domain output is not strict enough for compliance reporting, or when the user asks for an Internet.nl-grade audit' and 'For sub-10s answers, use scan_domain.' It also names cancel_deep_scan for aborting. This is exemplary usage guidance.

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