Suggests corrected code and practical examples for a JSON security finding based on the project's detected stack.
Dado um finding (JSON), sugere código corrigido com exemplo prático para a stack do projeto.
| Name | Required | Description | Default |
|---|---|---|---|
| finding | Yes | JSON string do Finding a corrigir | |
| project_path | Yes | Caminho do projeto (para detectar stack) |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations at all, so the description carries full burden. It does not state whether the tool is read-only, whether it modifies the project, whether it calls an LLM, or what format the suggestion takes. For a tool that ostensibly generates code, the side-effect profile is important and unaddressed.
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 concise sentence that front-loads the input (finding) and the output (corrected code). No wasted words, though it is almost too terse given the tool's complexity.
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?
No output schema, no annotations, and no description of return format or behavior. For a code-suggestion tool, the description should at least indicate the response shape (e.g., diff, snippet) and any limits. The agent is left with significant gaps.
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%, so baseline is 3. The description mentions 'finding (JSON)' and 'stack do projeto', which aligns with the two schema parameters, but adds no additional semantics (e.g., expected Finding shape, how project_path is used).
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 (sugere) and resource (código corrigido) tied to an input finding and the project's stack. This clearly distinguishes it from sibling validation tool sentinela_validate_fix and audit tools. Lacks explicit naming of the sibling, but the action is specific enough for an agent to pick it.
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 when-to-use guidance, no mention of prerequisites (e.g., needing a prior audit finding), and no differentiation from sentinela_validate_fix. The agent must infer that it is used after obtaining a finding from one of the audit tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.