Tool Redact

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

With no annotations, the description carries the full burden. It discloses critical behavior: pages with redactions are rasterized, text is physically and irrecoverably removed, other pages keep their text layer, and rasterize_all rasterizes the whole document.

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 compact sentences deliver the security promise, coordinate format, irreversibility, and the rasterize_all escalation. No filler.

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 core destructive behavior and region format are well covered, and an output schema reduces the need to document return values. Still, it omits output/overwrite flow, dpi effect, and path constraints, which matter for a destructive tool.

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 0%, and the description meaningfully documents regions=[{page,x,y,w,h}] with coordinate units and origin, plus rasterize_all semantics. However, dpi, path, output, and overwrite are not explained in either the schema or description.

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 verb/resource: secure redaction via coordinate regions, and clearly distinguishes itself by explaining physical deletion and rasterization, which separates it from sibling tools like tool_redact_text.

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?

It gives context that this is the security-level true redaction option and describes when rasterize_all=true is strongest, but it does not explicitly state when to prefer this tool over tool_redact_text or tool_sanitize.

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