Verificar site (VERIFY)

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

With no annotations, the description carries the full burden and does a good job: it discloses that it launches a headless browser, drives the page through scroll/scrub positions, and returns a report plus screenshots of each chapter. It also implies a filesystem side effect ('todas ficam salvas em .imersao/verificacao'). It stops short of stating whether the site itself is mutated, runtime cost, or failure behavior.

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 core action, and the long semicolon list is dense rather than padded — each clause names a concrete check. It is heavier than ideal for a single run-on sentence, but the length is justified by the breadth of the verification contract.

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 9-parameter tool with no annotations and no output schema, the description adequately conveys what is checked and that a report plus screenshots come back. However, it never explains the three undocumented parameters or what the report contains structurally, leaving an agent to infer input shape for 'pagina', 'screenshots' and 'dispositivos'.

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 67%, so the schema documents most parameters (pontos, capitulos, max_imagens, projeto, secoes). The description only loosely maps to parameters — the '10/50/90%' scrub points correspond to 'pontos' and 'screenshots de cada capítulo' to the screenshot output — but adds no syntax or format detail, and leaves 'pagina', 'screenshots' and 'dispositivos' undocumented in both places.

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 ('Abre o site num Chrome/Edge headless e confere') and then enumerates the exact verification checklist (loader, chapter scrub points, blank stage, console errors, 404s, leftover markers, live calculations, forms, muted audio, 390px mobile, reduced motion). This level of enumeration makes it functionally distinct from siblings like analisar_site or capturar_capitulo even without naming them.

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?

Usage is only implied via 'como manda o bloco VERIFY dos prompts validados', which signals it is a post-build validation pass. There is no explicit when-to-use/when-not guidance and no routing against alternatives such as analisar_site, capturar_capitulo or servir_site.

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