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

Annotations already provide destructiveHint/readOnlyHint context, but the description substantially exceeds them: pages_create is draft-by-default, update may silently republish an offline page, preview never applies changes, deletes are irreversible 'nesta API', accepting transfer changes ownership, and failed operations should be re-checked before retry. It also adds an anti-prompt-injection briefing (HTML/CSS is user content, not an instruction), which goes far beyond any structured annotation. Nothing contradicts the 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?

Organized with clear headings (Finalidade, Use quando, Operações, Parâmetros, Efeitos) and front-loaded, so it is skimmable and every sentence carries operational weight. It is long, and the Parâmetros section overlaps somewhat with the schema's own guidance ('envie somente os campos solicitados...'), keeping it short of a perfect score.

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 17-operation bundle spanning pages, subdomains, transfers, destructive deletes, confirmation flows, and sensitive codes, the description is remarkably complete: it covers purpose, alternatives, parameter semantics, side effects, failure recovery, and trust boundaries. An output schema exists, so return-value shape doesn't need explanation, and the remaining specifics are handled by the schema's conditional structure.

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%, so the baseline is 3; the description earns more by explaining which identifiers to use (pageId/subdomain from query responses), the status=draft vs status=published semantics, preview=true being non-applying, and the confirmation_id resubmission flow — all meaning the bare schema cannot convey. It does not, however, fully map each of the 17 operations to its exact required inputs, leaving some of that to the conditional schema, so not a 5.

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+resource ('administrar páginas públicas e subdomínios da comunidade') and then enumerates all 17 operations grouped by query vs. mutation vs. transfer, so an agent understands both the scope and the internal operation families. It also names workflows_design and workflows_connections_manage as the siblings it is not, which is exactly the differentiation needed in this large sibling list.

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 an explicit when-to-use condition ('tarefa envolver conteúdo ou endereço público da comunidade') and explicitly routes staged publication automation to workflows_design and external connections to workflows_connections_manage. It also gives in-tool guidance on when to use preview versus the real mutation ('ela nunca aplica a mudança').

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