redact_pdf

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

With no annotations provided, the description fully discloses key behavioral traits: permanent destruction of underlying data, self-verification, signed audit log, and local processing. It clearly conveys that this is a destructive, privacy-preserving operation, going beyond what annotations would typically provide.

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 three concise sentences, front-loaded with the core action. Each sentence adds value: what it does, how it works, and the privacy benefit. No fluff or redundancy.

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 largely complete for a tool with a rich output schema (signed audit log) and no annotations. It covers major behavioral aspects and privacy. However, it doesn't address potential ambiguity with sibling tools like verify_redaction or check_redaction, leaving a small gap in understanding when to use this tool versus those verification tools.

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?

The input schema covers all parameters (100% coverage), so the description does not need to add much. It mentions 'regions' and 'on-device' but does not provide additional detail beyond schema descriptions. The schema already explains coordinate system, page indexing, and required fields.

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 tool's purpose with a specific verb ('redact'), resource ('PDF'), and scope ('regions'). It also distinguishes from siblings like redact_by_entity by emphasizing region-based redaction versus entity-based.

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 clear context for when to use the tool (on-device, region-specific redaction) but does not explicitly mention alternatives or exclusions. It implies usage through the focus on 'regions' and 'on-device,' which differentiates it from sibling tools like redact_by_entity or verify_redaction.

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