Inspect prompt text and optional file paths for secrets, PII, blocked files, and payload size before sending to a chat provider.
Modo dry-run para inspecao de segredos, PII, arquivos proibidos e tamanho antes do envio.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Texto a ser inspecionado pelo sanitizador de segredos | |
| provider | No | Identificador do provedor (opcional) | |
| filePaths | No | Lista opcional de caminhos de arquivos para validacao contra a deny-list |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations supplied, the description carries the full burden. 'Modo dry-run' usefully signals that nothing is sent and the operation is a non-destructive preview, which is the most important behavioral trait. It does not say what happens when a secret or forbidden file is detected (block, warn, or just report), nor what the preview returns.
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 front-loaded sentence with no filler. It is dense and readable, though it packs four inspection targets into one clause rather than structuring them, and it is written in Portuguese while sibling tool names are English.
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?
There is no output schema, so the description would ideally say what the preview returns (a pass/fail report, findings list, size estimate). That gap is real, but for a simple three-parameter read-only preview tool the stated scope plus the fully-documented schema covers enough to call it correctly.
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 the schema already explains prompt, provider, and filePaths. The description only adds that inspection covers secrets, PII, forbidden files, and size, which loosely maps to prompt/filePaths but adds no format or constraint detail beyond the schema, leaving the baseline 3 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?
The description states a specific function: a dry-run inspection of a prompt for secrets, PII, forbidden files, and size before sending. That is concrete and distinct from the send-side sibling ask_web_chat, though the description never names the sibling to make the split explicit.
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 phrase 'antes do envio' (before sending) implies the natural usage point: run this prior to dispatching a request. However, no alternative tool is named, no when-not condition is given, and it is left to the agent to infer that ask_web_chat is the actual send operation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.