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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, so safety is covered; the description adds genuinely new behavior: page cap of 20, cursor-based continuation, and a truncation warning when the response exceeds 24k characters. It also discloses that the response carries identity, totals and a per-connection correction capability, which is not derivable from annotations. Minor blemish: 'limite até 20' sits awkwardly against the schema's maximum of 50.

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 packed into a few dense sentences with no filler. The heavy nested parentheticals, especially the paging/truncation clause, make it harder to parse than it needs to be, but every clause carries information.

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?

An output schema exists, yet the description still usefully summarizes the return shape (findings, identity, totals, correction capability), and it covers the pagination and truncation edge cases an agent would otherwise get wrong. For a zero-required-parameter read tool with full safety annotations, the only gap is the slight limite inconsistency.

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 only 57%, so the description has to compensate, and it does: it names the filter set (processoId, numeroPasta, regra, gravidade, status), states the PENDENTE default, and explains the limite/proximoCursor paging contract. The enum values themselves are left to the schema, which is fine, but the 'limite até 20' wording blurs the 20-per-page vs 50-maximum distinction the schema tries to make.

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?

Opens with a specific verb and resource ('Lista os achados do cadastro dos processos') and then enumerates the payload fields (campo, valor atual e proposto, natureza, confiança, gravidade, evidência), so an agent knows exactly what it gets back. It never names a sibling such as historico_cadastro or saude_integracoes to say how it differs, which keeps it from a 5.

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: you call it to review cadastro findings, and the default status=PENDENTE hints at a triage workflow. There is no explicit 'use this when…, use X instead' routing against the other cadastro/saúde siblings, so the agent must infer the selection rule.

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