delimit_redact

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

With no annotations, the description carries full burden. It explains the two actions (scan, redact) and lists detectable items, but does not detail what redaction entails (e.g., replacement tokens), side effects, or permissions. It is adequate but not comprehensive.

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?

The description is two sentences plus a bulleted list, all front-loaded with the core purpose. No redundant information; every line earns its place.

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?

For a simple tool with 3 optional parameters and an existing output schema, the description covers purpose, use case, and detection scope. It lacks explicit clarification of the redaction effect and the exact category values, but overall it is sufficient.

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 coverage is 100%, so description is not strictly required. However, it adds value by listing specific detectable patterns that map to the categories parameter (e.g., api_key, pii), and clarifies that 'scan' vs 'redact' are the action options, going beyond the schema's enum-less definition.

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 clearly states the action ('Scan or redact') and the resource ('sensitive data from text'), lists concrete examples (API keys, PII, etc.), and implicitly distinguishes from siblings like delimit_scan by specifying the LLM data leakage prevention context.

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 explicitly tells when to use: 'Use before sending prompts to external LLMs to prevent data leakage.' It does not mention when not to use or provide direct alternatives, but the use case is specific enough to guide selection.

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