verify_redaction

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

With no annotations, the description carries the full burden and excels: it discloses the two distinct execution paths, prerequisites (native engine + sidecar), fallback behavior, and the explicit caveat that the fallback is 'a good-faith re-check, not a claim of the same rigor.' It also notes 'on-device' operation, adding meaningful privacy context.

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 well-structured sentences that pack substantial information without waste. The em-dash and parenthetical structure breaks the sidecar and fallback modes cleanly, and every clause adds value. No redundancy with schema or sibling names.

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 the tool's complexity (two modes, prerequisites, caveats), the description covers all essential context: what it verifies, the strongest path, fallback behavior, and the rigor limitation. An output schema exists, so return values don't need explaining. This is complete for an AI agent to use correctly.

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% with a clear description for pdfPath ('absolute path to the redacted PDF to verify'). The tool description adds context about sidecars and modes but doesn't elaborate on the parameter itself beyond the schema. Baseline 3 is appropriate since the schema already handles parameter semantics fully.

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+resource: 'Re-scan an already-redacted PDF on-device and confirm nothing recoverable remains.' It clearly distinguishes the tool from siblings by introducing the sidecar-based rigorous path vs. the fallback general re-scan, making its scope and intent unmistakable.

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 provides clear usage context: use with a configured native engine and the file's sidecar for the strongest check, and falls back to a general re-scan otherwise. It explains when each mode applies, but doesn't explicitly name alternative tools like check_redaction or state exclusions, so it stops short of a full 5.

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