Guard Brasil

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

Annotations already establish readOnly, non-destructive, non-open-world behavior, so the bar is lower. The description adds meaningful context beyond annotations: the returned fields and a specific safety invariant ('never safe:true with unclassified residue, motivo: nao-medido'), which tells the agent how to interpret ambiguous results.

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?

Two short sentences with the purpose front-loaded and no filler. The 'motivo: nao-medido' token is a domain-specific jargon fragment that is slightly cryptic but compact.

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 carries the burden of naming return fields (safe/canShare/motivo/reason) and the key invariant, which it does. It is complete enough for a simple one-parameter predicate, though it omits any note on cost or latency.

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?

Only one parameter with 100% schema description coverage; the schema already documents 'text' as the text to check. The description adds no per-parameter detail but has nothing left to compensate for, so the 0-1 param baseline of 4 applies.

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: a boolean safety check on text for public sharing. An agent can distinguish this from guard_inspect and guard_scan_pii at a high level, though the description never explicitly contrasts the three siblings.

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?

There is no when-to-use guidance or condition selecting this tool over guard_inspect or guard_scan_pii. The phrase 'for public sharing' hints at context but does not state prerequisites, exclusions, or alternatives.

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

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

Annotations already establish the safety profile (readOnlyHint, destructiveHint=false, openWorldHint=false), so the bar is lower. The description goes beyond them by enumerating what the call returns — findings, textoMascarado, naoMedido residue, and a recommendation — plus the LGPD/ATRiAN validation framing. It still omits operational details like cost, limits, or whether masking is destructive to the input.

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?

Two compact, front-loaded sentences with no filler; the core action leads and the return contract follows. It loses a point only because the Portuguese jargon (textoMascarado, naoMedido, ATRiAN) is unexplained and slightly obscures meaning for an outside reader.

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 carries the return-value burden and does so by listing the four outputs. Combined with a fully documented input schema and safety annotations, it is nearly complete, missing only an explanation of what the ethics validation entails and any operational constraints.

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 coverage is 100%, so both parameters (text, mask) are already documented in the schema, establishing a baseline of 3. The description hints at masking through the 'textoMascarado' output but adds no syntax, defaults, or interaction detail beyond the schema.

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 names a specific verb (inspect) and resource (LGPD PII) and flags its scope as 'full', which distinguishes it implicitly from the lighter siblings guard_scan_pii and guard_check_safe. However, it never names those siblings, so the agent must infer the difference from the adjective 'full' alone.

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: 'Full ... inspection' suggests this is the comprehensive option versus the narrower scan/check siblings, but no explicit when-to-use, when-not-to-use, or alternative is stated. The agent can guess from the word 'full' but gets no hard routing rule.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered by structured data. The description adds that the result includes textoMascarado and naoMedido, which is useful return-shape context in the absence of an output schema, but it never explains what 'naoMedido' means or how masking is applied.

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?

Two short, front-loaded sentences with no filler. Some telegraphic tokens ('names A–J', 'naoMedido') cost readability but not word count, so it stays efficient.

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 one-parameter, no-output-schema tool with annotations, the essentials are mostly covered, and the description does disclose the two returned fields. However, undefined domain terms (naoMedido, 'names A–J') and the lack of any sibling disambiguation leave an agent guessing at scope.

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?

There is a single parameter with 100% schema description coverage ('Text to scan'), so the schema carries the semantics. The description adds nothing about the text parameter (size limits, encoding, whether it accepts multi-line or JSON). 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?

States a specific verb+resource ('PII scan') and enumerates the entity types it detects (CPF, CNPJ, RG, MASP, EMAIL, names A–J), which is concrete. It does not differentiate itself from the siblings guard_check_safe and guard_inspect, so an agent cannot tell from the description alone which of the three to pick.

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 word 'Quick' hints at a faster/lighter alternative to something, but no when-to-use condition, prerequisite, or named alternative is given. With two sibling guard tools, the absence of routing guidance is a real gap.

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