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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds genuinely useful context beyond them: that 'nada' is the default AND erases whatever is currently stored, and precisely which fields are retained or redacted in each mode (text omitted for recibos; phone, email, CPF and name stripped for recibos_e_historico). It does not say whether switching modes back restores prior data, which would have been the last useful detail.

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?

A single dense sentence, front-loaded with the verb and resource, then the three modes in parentheses. Every clause carries information, though the heavy parenthetical nesting makes it slightly harder to scan than a short list would be.

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 covers what an agent needs: the retention options, the destructive default, and the redaction rules. Annotations supply the mutation/idempotency profile, and the schema supplies the id format. Nothing required to call this correctly is missing.

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 50% — 'guardar' is a bare enum with no description. The tool description compensates fully by defining all three enum values in prose, which is exactly what the schema omits. The remaining parameter (meu_id) is already documented in the schema, so no further detail is needed.

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 (escolher/escolhe) and the exact resource it governs: what remains stored under your id. The three retention modes are spelled out with concrete semantics (default, one receipt per verdict, receipt plus text minus PII). It is not explicitly contrasted with the sibling meus_dados_apagar, whose deletion role overlaps with the 'nada' option, so an agent could momentarily conflate 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?

The description makes clear what each option stores, which implies when to pick one, but it never states when to call this tool versus meus_dados_ver (read) or meus_dados_apagar (delete). No prerequisites or ordering guidance (e.g., 'call after meus_dados_ver') is given, leaving usage to inference.

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