scan_output

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

No annotations are provided, so the description bears full burden. It discloses that PII is automatically redacted in findings, which is a key behavioral trait. However, it does not clarify whether the tool modifies the original text, whether redaction is reversible, what the return format looks like, or whether there are any rate limits or performance implications.

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 concise sentences front-load the purpose, then add the key behavioral detail about redaction. Every sentence is necessary and there is no filler. Perfectly sized for the complexity of the tool.

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?

Given only one simple string parameter and no output schema, the description covers the core intent and a notable behavior (redaction). It could optionally mention that results are returned as findings (referencing sibling get_findings), but is otherwise complete for a scanning tool with straightforward usage.

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% (one parameter 'text' with description 'The AI output text to scan.'). The tool description adds value by explaining what the scan checks for (PII leaks, content violations) and that redaction occurs, which goes beyond the schema's minimal description. Together, they give complete semantic clarity for the single parameter.

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 specifies a clear verb ('Check') and resource ('AI-generated output'), and enumerates the exact categories scanned (PII like email, SSN, credit card, phone, IP; policy violations like violence, self-harm, illegal activity). It distinguishes itself from siblings like scan_file, scan_code, scan_input, and check_secrets by focusing on AI output and listing specific PII types and policy categories.

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 description implies usage for scanning AI output, but does not explicitly state when to prefer this over alternatives like scan_input (which might scan user input) or check_secrets (which might scan for secrets). Provides no when-not-to-use guidance or preconditions.

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