Audit a project's error-handling domain to detect security and compliance gaps, returning structured findings for remediation.
Audita o domínio "error-handling" (Seção 31). Retorna findings estruturados.
| Name | Required | Description | Default |
|---|---|---|---|
| project_path | Yes | Caminho absoluto para o diretório raiz do projeto |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states only that it returns structured findings, without saying whether the operation is read-only, what 'findings' contain, whether the path must exist, or any cost/latency behavior. Minimal behavioral disclosure for a tool with zero annotation coverage.
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 no padding and the purpose front-loaded. The unexplained '(Seção 31)' is the only extraneous element.
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 and no annotations, the description should clarify what 'findings estruturados' actually contain and how they are surfaced. It leaves the return shape and behavioral profile entirely unspecified.
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% and the single project_path parameter is fully documented in the schema, so the baseline of 3 applies. The description adds nothing about the parameter (e.g., that it must point to a project root with analyzable source).
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 ('Audita') and resource ('domínio error-handling'), and the domain name distinguishes it from the many sibling audit_* tools that each target a different domain. The '(Seção 31)' reference is unexplained but does not obscure the core purpose.
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?
No guidance on when to run this single-domain audit versus sentinela_audit_full, nor any prerequisite or ordering (e.g., run sentinela_detect_stack first). Usage is only inferable from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.