redact_scan

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

With no annotations, the description carries the full burden and does well: it discloses non-destructive behavior, automatic OCR on scanned PDFs, the output categories (candidate list, metadata leakage, format-related list), and the NER model prerequisite plus noise caveat. No contradictions with annotations exist.

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 compact sentences with the most important safety property (non-destructive) front-loaded, followed by formats, outputs, and the NER caveat. 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 description covers purpose, formats, outputs, and a key parameter caveat, which is substantial for a tool with no annotations or output schema. However, it omits explanations for four parameters and does not describe return structure details beyond the high-level list, leaving an agent to infer important call semantics.

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 five parameters. It only adds meaning for enable_ner (model requirement, recommendation to disable). It does not explain keywords, ner_labels, enable_regex, or input_path beyond their property names.

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 (scan), a resource (documents), a key behavioral distinction (non-destructive, does not modify files), and the output (candidate sensitive items). This clearly differentiates it from siblings like redact_apply, which presumably applies changes.

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 clearly conveys the scanning context and supported document types, and gives an explicit conditional usage note (disable NER for standard/official documents due to noise). It does not explicitly name alternatives or say 'use redact_apply to apply redactions,' so it stops short of a full when/when-not comparison.

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