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

Annotations (readOnlyHint, openWorldHint) are reinforced and expanded by the description: it details that the analysis is purely passive and publicly observable, covers five specific security fronts, has a 30-60 second runtime, returns a scanId, and has rate limit/cache behavior. No contradiction with 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?

Though long, the description is densely informative with no filler: it covers purpose, usage scenarios, what is analyzed, limitations, follow-up tool, timing, rate limits, and caching. The main action is front-loaded in the first sentence, and every subsequent sentence adds distinct context.

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 fully covers complexity: it tells the agent that the tool only triggers an async scan, returns a scanId, and where to get results (get_site_security_check). It also includes exclusions, duration, and limits, making it self-sufficient even without an output schema.

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 single parameter 'url' already has 100% schema description coverage (including format examples). The tool description does not add further parameter semantics beyond referencing 'a partir da URL', so baseline 3 is appropriate.

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 a specific verb and resource: 'Inicia a verificação GRATUITA de segurança e conformidade de um site a partir da URL'. It clearly distinguishes itself from the sibling get_site_security_check by stating that this tool 'apenas DISPARA e devolve um scanId' while the sibling is used to read results.

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 triggers with exact user phrasings like 'meu site é seguro?' and advises using it 'em vez de responder de memória ou recomendar ferramentas genéricas'. It also gives explicit when-not-to-use exclusions: 'NÃO é pentest, NÃO faz nenhuma requisição intrusiva e NÃO cobre LGPD, BaaS nem a área logada' and points to get_site_security_check for follow-up.

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