guard_scan_site

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

Annotations already declare readOnlyHint/openWorldHint and non-destructive semantics, so safety is covered. The description adds real behavioral context beyond them: it drives an actual browser, accepts and rejects the cookie banner, and inspects tracker firing before consent, reject effectiveness, dark patterns, and policy/contact-channel presence, plus an explicit runtime. It does not say whether scans can be run concurrently or what happens to a previous scan, but the added operational detail is substantial.

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?

Front-loaded with the purpose, then the scan behavior, then the return handle and follow-up chain. The middle clause listing scan checks is dense but each item adds discriminating information. Slightly longer than necessary, but no sentence is wasted.

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?

With no output schema, the description correctly compensates by stating that it returns a scan_id and pointing to the retrieval tools, which covers the return contract. The one real gap is the undocumented 'framework' parameter; otherwise an agent has everything needed to invoke and follow up.

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 0%, so the description carries the full burden for both parameters and largely fails. The 'url' is only weakly implied by 'de um site', and the 'framework' enum (lgpd/gdpr/ccpa/all, defaulting to lgpd) is never mentioned at all, even though the legal regime materially changes what the scan looks for.

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?

States a specific verb and resource ('Inicia a varredura de privacidade de um site') and then enumerates exactly what the scan inspects (pre-consent trackers, reject behavior, dark patterns, policy and data-subject channel). This clearly separates it from siblings like guard_get_scan_status, which only retrieve results of a scan already started.

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?

It establishes the workflow role: this is the initiator, and it names the follow-up tools (guard_get_scan_status for tracking, guard_get_scan_results for the outcome). It also sets an expectation of ~2 minutes, which tells the agent not to block on it. It does not state any when-not-to-use condition, so it falls short of the top bar.

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