Redact sensitive data from text

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

With no annotations provided, the description carries the full burden. It discloses the output ('Returns the redacted text plus the data element types that were found') and implies external processing via 'using Strac DLP,' but it does not mention the irreversibility of redaction, the effect of different redact_field_mode values, or whether the original text is stored or transmitted. The core behavior is clear, yet edge behaviors are left to inference.

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?

Three sentences, no filler. The first sentence states the action, the second the return value, and the third the recommended usage context. Every sentence earns its place and the most critical information is front-loaded.

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?

The description is adequate for an initial selection decision, and an output schema is present to document return values. However, the lack of parameter semantics—especially include_matched_text and redact_field_mode—means an agent cannot fully understand invocation options without additional context. For a tool with no annotations, the description is not fully complete on its own.

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%, so the description must compensate for all three parameters. It only implicitly identifies 'text' as the input, and it says nothing about redact_field_mode or include_matched_text. The parameter names and enum values offer some self-evident meaning, but an agent receives no guidance on the semantics of include_matched_text or the trade-offs between modes, which is a significant gap at this coverage level.

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 opens with a specific verb ('Redact') and a precise resource ('PII, PHI, PCI and secrets out of a block of text'). It also states the return value, and the scope ('block of text') clearly distinguishes it from file-based siblings like redact_file and from detect-only siblings like detect_sensitive_data.

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 gives an explicit call-to-action: 'Call this before putting untrusted or user-supplied text into a prompt, a log line, a ticket or any downstream system.' This clearly establishes when to use the tool, though it does not mention alternatives or exclusions such as 'if you only need detection, use detect_sensitive_data.'

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