guard_check_compliance

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds genuine value beyond that: the privacy guarantee that nothing leaves the machine ('nada sai da máquina') and a description of the return shape (findings ordered by severity plus a 0-100 score). It stops short of disclosing pagination, limits, or how the two input modes behave.

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 purpose, then what it detects, then the output, then the sibling exclusion. No filler sentences, though the enumeration of checks is slightly longer than strictly needed.

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 usefully states what comes back (severity-ordered findings plus a 0-100 score), and annotations cover the safety profile. The main incompleteness is the input contract, which the description leaves entirely to the schema.

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 0% and there are two undocumented parameters (files and project_path), yet the description only says it 'reads the code' without explaining that either a files array or a project_path can be supplied, or how they differ. The description does not compensate for the coverage gap, leaving the agent to infer the input contract from raw schema keys.

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 (local LGPD compliance check of a project's code) and enumerates the exact classes of problems it detects (non-essential trackers firing without consent, forms collecting personal data without consent, missing privacy-policy link). It also distinguishes itself from guard_scan_site, so an agent can route correctly without opening either schema.

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?

Explicitly defines the negative case and the alternative: 'Não roda no site publicado (para isso use guard_scan_site); é uma checagem estática do código.' The when/when-not/alternative triple is fully specified.

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